textutils 1.2.3 → 1.2.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 13b50f88222d75883a9804ba452aa3dce5f4c517
-  data.tar.gz: 08c6eee7b70caf74b716fd4ed3a8d1d1d0c10967
+  metadata.gz: 16e24e7bc0a1004bc3fca49b6f3bfcaa6ce2e5ce
+  data.tar.gz: 6aa074466c9c89b089ecf0ac6d75164050abd0cb
 SHA512:
-  metadata.gz: 1ce49f78d634c23a8843893eb7afea9a3b8f9aa1fc9c713f6cd22ff47dadfbf4a893ce96b0f91ecfc118e6e65624b9474a1f0e80e83a6d7053a1894a19f3fe2b
-  data.tar.gz: 5361f93e31737603810fd17b2816677274612632d3cae45aff9b96031e253e36ada6fa3ad084bded187bc527338570cde761fb2c3e96f52f647fad798abca263
+  metadata.gz: f386324301ffc37deba32eb32202edf9b8706ff1b14971ba5a41db22a2d9a314be64914b4296e359cea2620a6b54ad89ae1cfa6e7c9fa1322ec4ef29020fb688
+  data.tar.gz: d56300976f712b8bb9de8f1e2e571948f35783090d1d7f1a238736f8efd6a60aba915d5ff807cb942a38f47f80b8d6917e6e1e846371b72b62022c8b3ad029f0

data/Manifest.txt

@@ -18,7 +18,9 @@ lib/textutils/helper/hypertext_helper.rb
 lib/textutils/helper/tag_helper.rb
 lib/textutils/helper/title_helper.rb
 lib/textutils/helper/unicode_helper.rb
-lib/textutils/helper/value_helper.rb
+lib/textutils/helper/value_helper_i.rb
+lib/textutils/helper/value_helper_ii.rb
+lib/textutils/helper/value_helper_iii_numbers.rb
 lib/textutils/helper/xml_helper.rb
 lib/textutils/page.rb
 lib/textutils/parser/name_parser.rb

data/lib/textutils.rb

@@ -43,7 +43,9 @@ require 'textutils/helper/unicode_helper'
 require 'textutils/helper/tag_helper'
 require 'textutils/helper/title_helper'
 require 'textutils/helper/address_helper'
-require 'textutils/helper/value_helper'
+require 'textutils/helper/value_helper_i'
+require 'textutils/helper/value_helper_ii'
+require 'textutils/helper/value_helper_iii_numbers'
 
 require 'textutils/utils'
 require 'textutils/core_ext/file'

data/lib/textutils/helper/value_helper_i.rb

@@ -0,0 +1,139 @@
+# encoding: utf-8
+
+
+module TextUtils
+  module ValueHelper
+
+  # if it looks like a key (only a-z lower case allowed); assume it's a key
+  #   - also allow . in keys e.g. world.quali.america, at.cup, etc.
+  #   - also allow 0-9 in keys e.g. at.2, at.3.1, etc.
+  #   - also allow leading digits e.g. 1850muenchen, 3kronen, etc.
+
+  TITLE_KEY_REGEX = /^(
+                     [a-z][a-z0-9.]*[a-z0-9]
+                       |
+                     [a-z]         # allow single letter keys e.g. n,s,etc.
+                       |
+                     [1-9][0-9]*[a-z]+  # NOTE: also allow starts with leading digits e.g. 1850muenchen, 3kronen etc.;
+                                   #   *MUST* be followed by letter;
+                                   #   note: leading zero for now *NOT* allowed
+                     )$
+                    /x
+
+
+  def find_key_n_title( values )  # note: returns ary [attribs,more_values] / two values
+    # todo/fix:
+    ##  change title to name 
+    ##  change synonyms to alt_names (!!!)
+    ##   => use new method e.g. find_key_n_name(s) - why?? why not??
+
+
+    ## fix: add/configure logger for ActiveRecord!!!
+    logger = LogKernel::Logger.root
+
+
+    ### support autogenerate key from first title value
+    if values[0] =~ TITLE_KEY_REGEX
+      key_col         = values[0]
+      title_col       = values[1]
+      more_values     = values[2..-1]
+    else
+      key_col         = '<auto>'
+      title_col       = values[0]
+      more_values     = values[1..-1]
+    end
+
+    attribs = {}
+
+    ## check title_col for grade (e.g. ***/**/*) and use returned stripped title_col if exits
+    grade, title_col = find_grade( title_col )
+
+    # NB: for now - do NOT include default grade e.g. if grade (***/**/*) not present; attrib will not be present too
+    if grade == 1 || grade == 2 || grade == 3  # grade found/present
+      logger.debug "   found grade #{grade} in title"
+      attribs[:grade] = grade
+    end
+
+ 
+    ## fix/todo: add find parts ??
+    #  e.g. ‹Estrella› ‹Damm› Inedit
+    #    becomes =>   title: 'Estrella Damm Inedit'  and  parts: ['Estrella','Damm']
+
+
+
+    ## title (split of optional tree hierarchy)
+    ##  e.g. Leverkusen › Köln/Bonn › Nordrhein-Westfalen
+    ##       Gelsenkirchen › Ruhrgebiet › Nordrhein-Westfalen
+    ##       München [Munich] › Bayern  etc.
+
+    ##  fix!!!! - trailing hierarchy get *ignored* for now!!! - fix!!
+    ##    pass along in  :tree (or :hierarchy) ??
+
+
+    ## note: must include leading and trailing space for now (fix!! later)
+    ##   hack for avoiding conflict w/ parts; fix: read/parse parts first
+    ##  todo: also allow > (as an alternative to ›)
+
+    title_tree = title_col.split( /[ ]+[›][ ]+/ )
+
+    ## title (split of optional synonyms)
+    # e.g. FC Bayern Muenchen|Bayern Muenchen|Bayern
+    #      München [Munich]
+    titles = NameTokenizer.new.tokenize( title_tree[0] )
+
+    attribs[ :title ]    =  titles[0]
+
+    ## add optional synonyms if present    
+    attribs[ :synonyms ] =  titles[1..-1].join('|')  if titles.size > 1
+
+    if key_col == '<auto>'
+      ## autogenerate key from first title
+      key_col = TextUtils.title_to_key( titles[0] )
+      logger.debug "   autogen key »#{key_col}« from title »#{titles[0]}«"
+    end
+
+    attribs[ :key ] = key_col
+
+    [attribs, more_values]
+  end
+
+
+  def find_grade( value )  # NB: returns ary [grade,value] / two values
+    grade = 4  # defaults to grade 4  e.g  *** => 1, ** => 2, * => 3, -/- => 4
+
+    # NB: stars must end field/value or start field/value
+    #  e.g.
+    #  *** Anton Bauer   or
+    #  Anton Bauer ***
+
+    value = value.sub( /^\s*(\*{1,3})\s+/ ) do |_|
+      if $1 == '***'
+        grade = 1
+      elsif $1 == '**'
+        grade = 2
+      elsif $1 == '*'
+        grade = 3
+      else
+        # unknown grade; not possible, is'it?
+      end
+      ''  # remove * from title if found
+    end
+
+    value = value.sub( /\s+(\*{1,3})\s*$/ ) do |_|
+      if $1 == '***'
+        grade = 1
+      elsif $1 == '**'
+        grade = 2
+      elsif $1 == '*'
+        grade = 3
+      else
+        # unknown grade; not possible, is'it?
+      end
+      ''  # remove * from title if found
+    end
+
+    [grade,value]
+  end
+
+  end # module ValueHelper
+end # module TextUtils

data/lib/textutils/helper/value_helper_ii.rb

@@ -0,0 +1,83 @@
+# encoding: utf-8
+
+
+module TextUtils
+  module ValueHelper
+
+  #####
+  ## fix!!!!: move to beerdb ??? why? why not?? - yes, move to beerdb-models
+
+  def match_brewery( value )
+    if value =~ /^by:/   ## by:  -brewed by/brewery
+      brewery_key = value[3..-1]  ## cut off by: prefix
+      brewery = BeerDb::Model::Brewery.find_by_key!( brewery_key )
+      yield( brewery )
+      true # bingo - match found
+    else
+      false # no match found
+    end
+  end
+
+
+  def is_year?( value )
+    # founded/established year e.g. 1776
+    match_result =  value =~ /^[0-9]{4}$/
+    # match found if 0,1,2,3 etc or no match if nil
+    # note: return bool e.g. false|true  (not 0,1,2,3 etc. and nil)
+    match_result != nil
+  end
+
+
+  def match_year( value )
+    if is_year?( value )  # founded/established year e.g. 1776
+      yield( value.to_i )
+      true # bingo - match found
+    else
+      false # no match found
+    end
+  end
+
+
+  def is_address?( value )
+    # if value includes // assume address e.g. 3970 Weitra // Sparkasseplatz 160
+    match_result =  value =~ /\/{2}/
+    # match found if 0,1,2,3 etc or no match if nil
+    # note: return bool e.g. false|true  (not 0,1,2,3 etc. and nil)
+    match_result != nil
+  end
+
+  def is_taglist?( value )
+    ### note: cannot start w/ number must be letter for now
+    ##  -- in the future allow free standing years (e.g. 1980 etc.?? why? why not?)
+    ##  e.g. not allowed  14 ha or 5_000 hl etc.
+    match_result =  value =~ /^([a-z][a-z0-9\|_ ]*[a-z0-9]|[a-z])$/
+    # match found if 0,1,2,3 etc or no match if nil
+    # note: return bool e.g. false|true  (not 0,1,2,3 etc. and nil)
+    match_result != nil
+  end
+
+
+  def is_website?( value )
+    # check for url/internet address e.g. www.ottakringer.at
+    #  - must start w/  www. or
+    #  - must end w/   .com
+    #
+    # fix: support more url format (e.g. w/o www. - look for .com .country code etc.)
+    match_result =  value =~ /^www\.|\.com$/
+    # match found if 0,1,2,3 etc or no match if nil
+    # note: return bool e.g. false|true  (not 0,1,2,3 etc. and nil)
+    match_result != nil
+  end
+
+  def match_website( value )
+    if is_website?( value )   # check for url/internet address e.g. www.ottakringer.at
+      # fix: support more url format (e.g. w/o www. - look for .com .country code etc.)
+      yield( value )
+      true # bingo - match found
+    else
+      false # no match found
+    end
+  end
+
+  end # module ValueHelper
+end # module TextUtils

data/lib/textutils/helper/value_helper_iii_numbers.rb

@@ -0,0 +1,78 @@
+# encoding: utf-8
+
+
+# match numbers (units)
+#  e.g  km_squared, abv, etc.
+
+module TextUtils
+  module ValueHelper
+
+
+  def match_number( value )
+    ## numeric
+    ##   note: can use any _ or spaces inside digits e.g. 1_000_000 or 1 000 000)
+    if value =~ /^([0-9][0-9 _]+[0-9])|([0-9]{1,2})$/
+      num = value.gsub(/[ _]/, '').to_i
+      yield( num )
+      true # bingo - match found
+    else
+      false # no match found
+    end
+  end
+
+
+  ###########################
+  ## numbers w/ units
+
+  def match_km_squared( value )
+    ## allow numbers like 453 km² or 45_000 km2
+    if value =~ /^([0-9][0-9 _]+[0-9]|[0-9]{1,2})(?:\s*(?:km2|km²)\s*)$/
+      num = value.gsub( 'km2', '').gsub( 'km²', '' ).gsub(/[ _]/, '').to_i
+      yield( num )
+      true # bingo - match found
+    else
+      false # no match found
+    end
+  end
+
+  def match_abv( value )  # alcohol by volume (abv) e.g. 5.2% 
+    if value =~ /^<?\s*(\d+(?:\.\d+)?)\s*%$/
+      # nb: allow leading < e.g. <0.5%
+      yield( $1.to_f )  # convert to decimal? how? use float?
+      true # bingo - match found
+    else
+      false # no match found
+    end
+  end
+
+  def match_og( value ) # plato (stammwuerze/gravity?) e.g. 11.2°
+    if value =~ /^(\d+(?:\.\d+)?)°$/
+      # nb: no whitespace allowed between ° and number e.g. 11.2°
+      yield( $1.to_f )  # convert to decimal? how? use float?
+      true # bingo - match found
+    else
+      false # no match found
+    end
+  end
+
+  def match_kcal( value )
+    if value =~ /^(\d+(?:\.\d+)?)\s*kcal(?:\/100ml)?$/  # kcal
+      # nb: allow 44.4 kcal/100ml or 44.4 kcal or 44.4kcal
+      yield( $1.to_f )  # convert to decimal? how? use float?
+      true # bingo - match found
+    else
+      false # no match found
+    end
+  end
+
+  def match_hl( value )  # hector liters (hl) 1hl = 100l
+    if value =~ /^(?:([0-9][0-9_ ]+[0-9]|[0-9]{1,2})\s*hl)$/  # e.g. 20_000 hl or 50hl etc.
+      yield( $1.gsub( /[ _]/, '' ).to_i )
+      true # bingo - match found
+    else
+      false # no match found
+    end
+  end
+
+  end # module ValueHelper
+end # module TextUtils

data/lib/textutils/parser/name_parser.rb

@@ -2,6 +2,55 @@
 
 # fix: move into TextUtils namespace/module!! ??
 
+
+class NameTokenizer   ## - rename to NameScanner, NameSplitter, NameSeparator, etc.
+
+  ## split (single) string value into array of names
+  ##   e.g.
+  ##   'München [Munich]'             => ['München', '[Munich]']
+  ##   'Wr. Neustadt | Wiener Neustadt' => ['Wr. Neustadt', 'Wiener Neustadt']
+  include LogUtils::Logging
+
+  def tokenize( value )   ## rename to/use split - why? why not??
+    names = []
+
+    # 1)  split by | (pipe) -- remove leading n trailing whitespaces
+    parts = value.split( /[ \t]*\|[ \t]*/ )
+
+    # 2)  split "inline" translations e.g. München [Munich]
+
+    ## todo: add support for  Munich [en]  e.g. trailing lang tag
+    ## todo: add support for bullet (official bi-lingual names w/ tags ??) - see brussels - why, why not??
+
+    parts.each do |part|
+        s = StringScanner.new( part )
+        s.skip( /[ \t]+/)   # skip whitespaces
+
+        while s.eos? == false
+          if s.check( /\[/ )
+            ## scan everything until the end of bracket (e.g.])
+            name = s.scan( /\[[^\]]+\]/)
+            ## todo/fix: if name nil - issue warning??
+            #  starting w/ [  but no closing ] found !!!! - possible? fix!!
+          else
+            ## scan everything until the begin of bracket (e.g.[)
+            name = s.scan( /[^\[]+/)
+            name = name.rstrip   ## remove trailing spaces (if present)
+          end
+          names << name
+
+          s.skip( /[ \t]+/)  # skip whitespaces
+          logger.debug( "[NameTokenizer] eos?: #{s.eos?}, rest: >#{s.rest}<" )
+        end
+    end # each part
+
+    logger.debug( "[NameTokenizer] names=#{names.inspect}")
+    names
+  end # method split
+end # class NameTokenizer
+
+
+=begin
 class NameParser
 
   include LogUtils::Logging
@@ -9,4 +58,4 @@ class NameParser
   ## to be done
   
 end # class NameParser
-
+=end

data/lib/textutils/version.rb

@@ -4,7 +4,7 @@ module TextUtils
 
   MAJOR = 1 ## todo: namespace inside version or something - why? why not??
   MINOR = 2
-  PATCH = 3
+  PATCH = 4
   VERSION = [MAJOR,MINOR,PATCH].join('.')
 
   def self.version

data/test/test_title_finder.rb

@@ -1,5 +1,9 @@
 # encoding: utf-8
 
+###
+# to run use
+# ruby -I ./lib -I ./test test/test_title_finder.rb
+
 
 require 'helper'
 
@@ -8,18 +12,43 @@ class TestTitleFinder < Minitest::Test
 
   include TextUtils::ValueHelper   #  lets us use find_grade, etc.
 
-  def test_grade
 
+  def test_find_key_n_title
+    attribs, _ = find_key_n_title( ['München [Munich]'] )  ## skip returned more_values (use _)
+    assert_equal 'muenchen',  attribs[:key]
+    assert_equal 'München',   attribs[:title]
+    assert_equal '[Munich]',  attribs[:synonyms]
+  end
+
+  def test_find_key_n_title_w_tree
+    attribs, _ = find_key_n_title( ['München [Munich] › Oberbayern › Bayern'] )  ## skip returned more_values (use _)
+    assert_equal 'muenchen',  attribs[:key]
+    assert_equal 'München',   attribs[:title]
+    assert_equal '[Munich]',  attribs[:synonyms]
+  end
+
+
+  def test_title_tokenizer
+    names = NameTokenizer.new.tokenize( 'München [Munich]' )
+    assert_equal 2, names.size
+    assert_equal 'München',  names[0]
+    assert_equal '[Munich]', names[1]
+
+    names = NameTokenizer.new.tokenize( 'FC Bayern Muenchen|Bayern Muenchen|Bayern' )
+    assert_equal 3, names.size
+    assert_equal 'FC Bayern Muenchen', names[0]
+    assert_equal 'Bayern Muenchen',    names[1]
+    assert_equal 'Bayern',             names[2]
+  end
+
+  def test_grade
     assert_equal [1,'Anton Bauer'], find_grade( '*** Anton Bauer' )
     assert_equal [2,'Anton Bauer'], find_grade( '** Anton Bauer' )
     assert_equal [3,'Anton Bauer'], find_grade( '* Anton Bauer' )
     assert_equal [4,'Anton Bauer'], find_grade( 'Anton Bauer' )
 
     assert_equal [1,'Anton Bauer'], find_grade( 'Anton Bauer ***' )
-
   end
 
-
-
 end # class TestTitleFinder
 

data/test/test_title_helper.rb

@@ -62,7 +62,8 @@ class TestTitleHelper < Minitest::Test
       [ "Ṣan'ā' [Sana'a]", 'sana'],
       [ "P'yŏngyang [Pyongyang]", 'pyongyang' ],
       [ 'Kāṭhmāḍaũ [Kathmandu]', 'kathmadau' ],
-      [ "Pe\u{030C}awar", 'pexawar']  ## note: use unicode literal; Pex̌awar  -- see en.wikipedia.org/wiki/Peshawar
+      [ "Pe\u{030C}awar", 'pexawar'],  ## note: use unicode literal; Pex̌awar  -- see en.wikipedia.org/wiki/Peshawar
+      [ '1850 München', '1850muenchen'],
     ]
 
     txt_io.each do |txt|

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: textutils
 version: !ruby/object:Gem::Version
-  version: 1.2.3
+  version: 1.2.4
 platform: ruby
 authors:
 - Gerald Bauer
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-06-11 00:00:00.000000000 Z
+date: 2015-06-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: props
@@ -124,7 +124,9 @@ files:
 - lib/textutils/helper/tag_helper.rb
 - lib/textutils/helper/title_helper.rb
 - lib/textutils/helper/unicode_helper.rb
-- lib/textutils/helper/value_helper.rb
+- lib/textutils/helper/value_helper_i.rb
+- lib/textutils/helper/value_helper_ii.rb
+- lib/textutils/helper/value_helper_iii_numbers.rb
 - lib/textutils/helper/xml_helper.rb
 - lib/textutils/page.rb
 - lib/textutils/parser/name_parser.rb

data/lib/textutils/helper/value_helper.rb

@@ -1,249 +0,0 @@
-# encoding: utf-8
-
-
-module TextUtils
-  module ValueHelper
-
-  #####
-  ## fix: move to beerdb ??? why? why not?? - yes, move to beerdb-models
-
-  def match_brewery( value )
-    if value =~ /^by:/   ## by:  -brewed by/brewery
-      brewery_key = value[3..-1]  ## cut off by: prefix
-      brewery = BeerDb::Model::Brewery.find_by_key!( brewery_key )
-      yield( brewery )
-      true # bingo - match found
-    else
-      false # no match found
-    end
-  end
-
-
-  def is_year?( value )
-    # founded/established year e.g. 1776
-    match_result =  value =~ /^[0-9]{4}$/
-    # match found if 0,1,2,3 etc or no match if nil
-    # note: return bool e.g. false|true  (not 0,1,2,3 etc. and nil)
-    match_result != nil
-  end
-
-
-  def match_year( value )
-    if is_year?( value )  # founded/established year e.g. 1776
-      yield( value.to_i )
-      true # bingo - match found
-    else
-      false # no match found
-    end
-  end
-
-
-  def match_km_squared( value )
-    ## allow numbers like 453 km² or 45_000 km2
-    if value =~ /^([0-9][0-9 _]+[0-9]|[0-9]{1,2})(?:\s*(?:km2|km²)\s*)$/
-      num = value.gsub( 'km2', '').gsub( 'km²', '' ).gsub(/[ _]/, '').to_i
-      yield( num )
-      true # bingo - match found
-    else
-      false # no match found
-    end
-  end
-
-  def match_number( value )
-    ## numeric (nb: can use any _ or spaces inside digits e.g. 1_000_000 or 1 000 000)
-    if value =~ /^([0-9][0-9 _]+[0-9])|([0-9]{1,2})$/
-      num = value.gsub(/[ _]/, '').to_i
-      yield( num )
-      true # bingo - match found
-    else
-      false # no match found
-    end
-  end
-
-
-  def match_abv( value )  # alcohol by volume (abv) e.g. 5.2% 
-    if value =~ /^<?\s*(\d+(?:\.\d+)?)\s*%$/
-      # nb: allow leading < e.g. <0.5%
-      yield( $1.to_f )  # convert to decimal? how? use float?
-      true # bingo - match found
-    else
-      false # no match found
-    end
-  end
-
-  def match_og( value ) # plato (stammwuerze/gravity?) e.g. 11.2°
-    if value =~ /^(\d+(?:\.\d+)?)°$/
-      # nb: no whitespace allowed between ° and number e.g. 11.2°
-      yield( $1.to_f )  # convert to decimal? how? use float?
-      true # bingo - match found
-    else
-      false # no match found
-    end
-  end
-
-  def match_kcal( value )
-    if value =~ /^(\d+(?:\.\d+)?)\s*kcal(?:\/100ml)?$/  # kcal
-      # nb: allow 44.4 kcal/100ml or 44.4 kcal or 44.4kcal
-      yield( $1.to_f )  # convert to decimal? how? use float?
-      true # bingo - match found
-    else
-      false # no match found
-    end
-  end
-
-  def match_hl( value )  # hector liters (hl) 1hl = 100l
-    if value =~ /^(?:([0-9][0-9_ ]+[0-9]|[0-9]{1,2})\s*hl)$/  # e.g. 20_000 hl or 50hl etc.
-      yield( $1.gsub( /[ _]/, '' ).to_i )
-      true # bingo - match found
-    else
-      false # no match found
-    end
-  end
-
-
-  def is_website?( value )
-    # check for url/internet address e.g. www.ottakringer.at
-    #  - must start w/  www. or
-    #  - must end w/   .com
-    #
-    # fix: support more url format (e.g. w/o www. - look for .com .country code etc.)
-    match_result =  value =~ /^www\.|\.com$/
-    # match found if 0,1,2,3 etc or no match if nil
-    # note: return bool e.g. false|true  (not 0,1,2,3 etc. and nil)
-    match_result != nil
-  end
-
-  def match_website( value )
-    if is_website?( value )   # check for url/internet address e.g. www.ottakringer.at
-      # fix: support more url format (e.g. w/o www. - look for .com .country code etc.)
-      yield( value )
-      true # bingo - match found
-    else
-      false # no match found
-    end
-  end
-
-
-
-  def is_address?( value )
-    # if value includes // assume address e.g. 3970 Weitra // Sparkasseplatz 160
-    match_result =  value =~ /\/{2}/
-    # match found if 0,1,2,3 etc or no match if nil
-    # note: return bool e.g. false|true  (not 0,1,2,3 etc. and nil)
-    match_result != nil
-  end
-
-  def is_taglist?( value )
-    ### note: cannot start w/ number must be letter for now
-    ##  -- in the future allow free standing years (e.g. 1980 etc.?? why? why not?)
-    ##  e.g. not allowed  14 ha or 5_000 hl etc.
-    match_result =  value =~ /^([a-z][a-z0-9\|_ ]*[a-z0-9]|[a-z])$/
-    # match found if 0,1,2,3 etc or no match if nil
-    # note: return bool e.g. false|true  (not 0,1,2,3 etc. and nil)
-    match_result != nil
-  end
-
-
-  def find_grade( value )  # NB: returns ary [grade,value] / two values
-    grade = 4  # defaults to grade 4  e.g  *** => 1, ** => 2, * => 3, -/- => 4
-
-    # NB: stars must end field/value or start field/value
-    #  e.g.
-    #  *** Anton Bauer   or
-    #  Anton Bauer ***
-
-    value = value.sub( /^\s*(\*{1,3})\s+/ ) do |_|
-      if $1 == '***'
-        grade = 1
-      elsif $1 == '**'
-        grade = 2
-      elsif $1 == '*'
-        grade = 3
-      else
-        # unknown grade; not possible, is'it?
-      end
-      ''  # remove * from title if found
-    end
-
-    value = value.sub( /\s+(\*{1,3})\s*$/ ) do |_|
-      if $1 == '***'
-        grade = 1
-      elsif $1 == '**'
-        grade = 2
-      elsif $1 == '*'
-        grade = 3
-      else
-        # unknown grade; not possible, is'it?
-      end
-      ''  # remove * from title if found
-    end
-
-    [grade,value]
-  end
-
-
-  def find_key_n_title( values )  # NB: returns ary [attribs,more_values] / two values
-
-    ## fix: add/configure logger for ActiveRecord!!!
-    logger = LogKernel::Logger.root
-
-    ### todo/fix: allow check - do NOT allow mixed use of with key and w/o key
-    ##  either use keys or do NOT use keys; do NOT mix in a single fixture file
-
-    ### support autogenerate key from first title value
-
-    # if it looks like a key (only a-z lower case allowed); assume it's a key
-    #   - also allow . in keys e.g. world.quali.america, at.cup, etc.
-    #   - also allow 0-9 in keys e.g. at.2, at.3.1, etc.
-
-    # fix/todo: add support for leading underscore _
-    #   or allow keys starting w/ digits?
-    
-    # NB: key must start w/ a-z letter (NB: minimum one letter possible)
-    if values[0] =~ /^([a-z][a-z0-9.]*[a-z0-9]|[a-z])$/
-      key_col         = values[0]
-      title_col       = values[1]
-      more_values     = values[2..-1]
-    else
-      key_col         = '<auto>'
-      title_col       = values[0]
-      more_values     = values[1..-1]
-    end
-
-    attribs = {}
-
-    ## check title_col for grade (e.g. ***/**/*) and use returned stripped title_col if exits
-    grade, title_col = find_grade( title_col )
-
-    # NB: for now - do NOT include default grade e.g. if grade (***/**/*) not present; attrib will not be present too
-    if grade == 1 || grade == 2 || grade == 3  # grade found/present
-      logger.debug "   found grade #{grade} in title"
-      attribs[:grade] = grade
-    end
-
-    ## fix/todo: add find parts ??
-    #  e.g. ‹Estrella› ‹Damm› Inedit
-    #    becomes =>   title: 'Estrella Damm Inedit'  and  parts: ['Estrella','Damm']
-
-    ## title (split of optional synonyms)
-    # e.g. FC Bayern Muenchen|Bayern Muenchen|Bayern
-    titles = title_col.split('|')
-
-    attribs[ :title ]    =  titles[0]
-
-    ## add optional synonyms if present
-    attribs[ :synonyms ] =  titles[1..-1].join('|')  if titles.size > 1
-
-    if key_col == '<auto>'
-      ## autogenerate key from first title
-      key_col = TextUtils.title_to_key( titles[0] )
-      logger.debug "   autogen key »#{key_col}« from title »#{titles[0]}«"
-    end
-
-    attribs[ :key ] = key_col
-
-    [attribs, more_values]
-  end
-
-  end # module ValueHelper
-end # module TextUtils