textutils 0.7.1 → 0.8.0

data/Manifest.txt

@@ -1,6 +1,6 @@
-History.markdown
+History.md
 Manifest.txt
-README.markdown
+README.md
 Rakefile
 lib/textutils.rb
 lib/textutils/classifier.rb
@@ -29,3 +29,4 @@ test/helper.rb
 test/test_hypertext_helper.rb
 test/test_title_helper.rb
 test/test_unicode_helper.rb
+test/test_values_reader.rb

data/{README.markdown → README.md}

@@ -1,4 +1,6 @@
-# `textutils` - Text Filters, Helpers, Readers and More in Ruby
+# `textutils`
+
+Text Filters, Helpers, Readers and More in Ruby
 
 * home  :: [github.com/rubylibs/textutils](https://github.com/rubylibs/textutils)
 * bugs  :: [github.com/rubylibs/textutils/issues](https://github.com/rubylibs/textutils/issues)
@@ -7,6 +9,7 @@
 * forum :: [ruby-talk@ruby-lang.org](www.ruby-lang.org/en/community/mailing-lists/)
 
 
+
 ## Filters
 
 ### `comments_percent_style` Filter

data/Rakefile

@@ -14,8 +14,8 @@ Hoe.spec 'textutils' do
   self.email   = 'ruby-talk@ruby-lang.org'
 
   # switch extension to .markdown for gihub formatting
-  self.readme_file  = 'README.markdown'
-  self.history_file = 'History.markdown'
+  self.readme_file  = 'README.md'
+  self.history_file = 'History.md'
 
   self.extra_deps = [
     ['logutils', '~> 0.5']  # e.g. >= 0.5 <= 1.0

data/lib/textutils/helper/title_helper.rb

@@ -10,13 +10,20 @@ module TextUtils
 #   lets us use "classic" web helpers a la rails
 #   find a good name for sub module -  Reader? Fixtures? Values? Parser? 
 
+  def strip_part_markers( title )   # use different name e.g. strip_name_markers/strip_name_enclosure etc.??
+     # remove optional part markers
+     # e.g. Bock ‹Damm› becomes =>  Bock Damm
+     #      ‹Estrella› ‹Damm› Inedit becomes =>  Estrella Damm Inedit
 
+     # todo: also allow reguluar <> for easy typing/input ??? why? why not? used for anything else already?
+     title.gsub( /[‹›]/, '' )
+  end
 
   def strip_translations( title )
       # remove optional english translation in square brackets ([])
       # e.g. Wien [Vienna]  =>  Wien
 
-      title.gsub( /\[.+\]/, '' )
+      title.gsub( /\[[^\]]+\]/, '' )
   end
 
   def strip_subtitles( title )
@@ -24,7 +31,7 @@ module TextUtils
       # e.g. Las Palmas (de Gran Canaria) => Las Palmas
       #      Palma (de Mallorca) => Palma
 
-      title.gsub( /\(.+\)/, '' )
+      title.gsub( /\([^\)]+\)/, '' )
   end
 
   def strip_tags( title )   # todo: use an alias or rename for better name ??
@@ -34,7 +41,7 @@ module TextUtils
       #
       # todo: use for autotags? e.g. {Bio} => bio 
       
-      title.gsub( /\{.+\}/, '' )
+      title.gsub( /\{[^\}]+\}/, '' )
   end
 
   def strip_whitespaces( title )
@@ -54,6 +61,8 @@ module TextUtils
       ## NB: downcase does NOT work for accented chars (thus, include in alternatives)
       key = title.downcase
 
+      key = strip_part_markers( key )  # e.g. ‹Estrella› ‹Damm› Inedit becomes =>  Estrella Damm Inedit
+
       key = strip_translations( key )
 
       key = strip_subtitles( key )

data/lib/textutils/helper/value_helper.rb

@@ -12,7 +12,7 @@ module TextUtils
   def match_country( value )
     if value =~ /^country:/       # country:
       country_key = value[8..-1]  # cut off country: prefix
-      country = WorldDb::Models::Country.find_by_key!( country_key )
+      country = WorldDb::Model::Country.find_by_key!( country_key )
       yield( country )
       true # bingo - match found
     else
@@ -23,7 +23,7 @@ module TextUtils
   def match_supra( value )
     if value =~ /^supra:/         # supra:
       country_key = value[6..-1]  # cut off supra: prefix
-      country = WorldDb::Models::Country.find_by_key!( country_key )
+      country = WorldDb::Model::Country.find_by_key!( country_key )
       yield( country )
       true # bingo - match found
     else
@@ -52,11 +52,11 @@ module TextUtils
   def match_region_for_country( value, country_id )  ## NB: required country_id 
     if value =~ /^region:/   ## region:
       region_key = value[7..-1]  ## cut off region: prefix
-      region = WorldDb::Models::Region.find_by_key_and_country_id!( region_key, country_id )
+      region = WorldDb::Model::Region.find_by_key_and_country_id!( region_key, country_id )
       yield( region )
       true  # bingo - match found
     elsif is_region?( value )  ## assume region code e.g. TX or N
-      region = WorldDb::Models::Region.find_by_key_and_country_id!( value.downcase, country_id )
+      region = WorldDb::Model::Region.find_by_key_and_country_id!( value.downcase, country_id )
       yield( region )
       true  # bingo - match found
     else
@@ -68,7 +68,7 @@ module TextUtils
   def match_city( value )  # NB: might be nil (city not found)
     if value =~ /^city:/   ## city:
       city_key = value[5..-1]  ## cut off city: prefix
-      city = WorldDb::Models::City.find_by_key( city_key )
+      city = WorldDb::Model::City.find_by_key( city_key )
       yield( city )  # NB: might be nil (city not found)
       true # bingo - match found
     else
@@ -80,7 +80,7 @@ module TextUtils
   def match_metro( value )
     if value =~ /^metro:/   ## metro:
       city_key = value[6..-1]  ## cut off metro: prefix
-      city = WorldDb::Models::City.find_by_key!( city_key )   # NB: parent city/metro required, that is, lookup w/ !
+      city = WorldDb::Model::City.find_by_key!( city_key )   # NB: parent city/metro required, that is, lookup w/ !
       yield( city )
       true # bingo - match found
     else
@@ -113,7 +113,7 @@ module TextUtils
   def match_brewery( value )
     if value =~ /^by:/   ## by:  -brewed by/brewery
       brewery_key = value[3..-1]  ## cut off by: prefix
-      brewery = BeerDb::Models::Brewery.find_by_key!( brewery_key )
+      brewery = BeerDb::Model::Brewery.find_by_key!( brewery_key )
       yield( brewery )
       true # bingo - match found
     else
@@ -288,6 +288,10 @@ module TextUtils
       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('|')

data/lib/textutils/reader/values_reader.rb

@@ -58,11 +58,20 @@ class ValuesReader
 
 
   def initialize( path, more_attribs={} )
-    @path = path
-
     @more_attribs = more_attribs
 
-    @data = File.read_utf8( @path )
+    ### workaround/hack
+    #  if path includes newline assume it's a string buffer not a file name
+    #  fix: use  from_file an from_string etc. for  ctor
+    #   check  what is the best convention (follow  ???)
+
+    if path =~ /\n/m
+      @path = 'stringio'   # what name to use ???
+      @data = path.dup   # make a duplicate ?? why? why not?
+    else
+      @path = path
+      @data = File.read_utf8( @path )
+    end
   end
 
 
@@ -76,13 +85,12 @@ class ValuesReader
 
   def each_line   # support multi line records
 
-    inside_line = false   # todo: find a better name? e.g. line_found?
-    attribs = {}
-    more_values = []
-      
+    inside_record  = false
+    blank_counter  = 0    # count of number of blank lines (note: 1+ blank lines clear multi-line record)
+    values         = []
 
     @data.each_line do |line|
-  
+
       ## allow alternative comment lines
       ## e.g. -- comment or
       ##      % comment
@@ -91,7 +99,10 @@ class ValuesReader
       ## NB: for now alternative comment lines not allowed as end of line style e.g
       ##  some data, more data   -- comment here
 
-      if line =~ /^\s*#/ || line =~ /^\s*--/ || line =~ /^\s*%/
+      if line =~ /^\s*#/  ||
+         line =~ /^\s*--/ ||
+         line =~ /^\s*%/  ||
+         line =~ /^\s*__/
         # skip komments and do NOT copy to result (keep comments secret!)
         logger.debug 'skipping comment line'
         next
@@ -99,7 +110,8 @@ class ValuesReader
 
       if line =~ /^\s*$/
         # kommentar oder leerzeile überspringen 
-        logger.debug 'skipping blank line'
+        blank_counter += 1
+        logger.debug "skipping blank line (#{blank_counter})"
         next
       end
 
@@ -114,71 +126,109 @@ class ValuesReader
       line = line.strip
 
 
+      if line =~ /^-\s/   # check for group headers  e.g.  - St. James Brewery
+        logger.info "  skip group header #{line} for now (fix/add soon)"
+        next
+      elsif line =~ /^\[([a-z][a-z]+)\]/
       ### check for multiline record
-      ##    must start with key and colon   e.g.   brands: 
-      if line =~ /^[a-z][a-z0-9.]*[a-z0-9]:/
-         # NB: every additional line is one value e.g. city:wien, etc.
-         #  allows you to use any chars
-         logger.debug "   multi-line record - add key-value »#{line}«"
-
-         more_values.unshift( line.dup )   # add value upfront to array (first value); lets us keep (optional) tags as last entry; fix!! see valuereaderEx v2
-         next
-      else
-        # NB: new record clears/ends multi-line record
-
-        if inside_line  # check if we already processed a line? if yes; yield last line
+      ##    must start with key e.g. [guiness]
+      ##   for now only supports key with letter a-z (no digits/numbers or underscore or dots)
+ 
+        if values.length > 0  # check if we already processed a record? if yes; yield last record (before reset)
+          attribs, more_values = find_key_n_title( values )
+          attribs = attribs.merge( @more_attribs )  # e.g. merge country_id and other defaults if present
           yield( attribs, more_values )
-          attribs     = {}
-          more_values = []
+          values         = []
+        end
+
+        inside_record  = true
+        blank_counter  = 0
+
+        # NB: every additional line is one value e.g. city:wien, etc.
+        #  allows you to use any chars
+        logger.debug "   multi-line record w/ key »#{$1}«"
+
+        values         = [$1.dup]    # add key as first value in ary
+      elsif inside_record && blank_counter == 0 && line =~ /\/{2}/ # check address line (must contain //)
+        values += [line.dup]     # assume single value column (no need to escape commas)
+      elsif inside_record && blank_counter == 0 && line =~ /^[a-z][a-z0-9.]*[a-z0-9]:/ # check key: value pair
+        values += [line.dup]     # assume single value column (no need to escape commas)
+      else
+        if inside_record && blank_counter == 0   # continue adding more values
+          values += find_values( line )
+        else                                     # assume single-line (stand-alone / classic csv) record          
+          if values.length > 0
+            attribs, more_values = find_key_n_title( values )
+            attribs = attribs.merge( @more_attribs )  # e.g. merge country_id and other defaults if present
+            yield( attribs, more_values )
+            values         = []
+          end
+          inside_record  = false
+          blank_counter  = 0
+          values = find_values( line )
         end
-        inside_line = true
       end
 
+    end # each lines
 
-      ### guard escaped commas (e.g. \,)
-      line = line.gsub( '\,', '♣' )  # use black club suit/=shamrock char for escaped separator
-      
-      ## use generic separator (allow us to configure separator)
-      line = line.gsub( ',', '›')
-      
-      ## restore escaped commas (before split)
-      line = line.gsub( '♣', ',' )
+    # do NOT forget to yield last line (if present/processed)
+    if values.length > 0
+      attribs, more_values = find_key_n_title( values )
+      attribs = attribs.merge( @more_attribs )  # e.g. merge country_id and other defaults if present
+      yield( attribs, more_values )
+    end
 
-      logger.debug "line: »#{line}«"
+  end # method each_line
 
-      values = line.split( '›' )
-      
-      # pass 1) remove leading and trailing whitespace for values
 
-      values = values.map { |value| value.strip }
+  ### todo:
+  ##   move to helper for reuse a la find_key_n_title ???  
+  ##  use different/better name ?? e.g. find_values_in_line  or split_line_into_values ??
+  def find_values( line )
+    ## note returns an array of values (strings)
 
-      ##### todo remove support of comment column? (NB: must NOT include commas)
-      # pass 2) remove comment columns
-      
-      values = values.select do |value|
-        if value =~ /^#/  ## start with # treat it as a comment column; e.g. remove it
-          logger.debug "   removing column with value »#{value}«"
-          false
-        else
-          true
-        end
-      end
+    meta_comma     = '«KOMMA»'
+    meta_separator = '« »'
 
-      logger.debug "  values: »#{values.join('« »')}«"
+    # guard escaped commas
+    #  e.g. convert \, to «KOMMA»
+    line = line.gsub( '\,', meta_comma )
 
-      attribs, more_values = find_key_n_title( values )
+    # note: use generic separator (allow us to configure separator)
+    #  e.g « »
+    line = line.gsub( ',', meta_separator )
 
-      attribs = attribs.merge( @more_attribs )  # e.g. merge country_id and other defaults if present
+    # restore escaped commas (before split)
+    line = line.gsub( meta_comma, ',' )
 
-    end # each lines
+    logger.debug "line: |»#{line}«|"
 
-    # do NOT forget to yield last line (if present/processed)
-    if inside_line
-      yield( attribs, more_values )
-    end
+    values = line.split( meta_separator )
 
+    # pass 1) remove leading and trailing whitespace for values
 
-  end # method each_line
+    values = values.map { |value| value.strip }
+
+
+    ##### todo/fix:
+    #  !!!REMOVE!!!
+    # remove support of comment column? (NB: must NOT include commas)
+    # pass 2) remove comment columns
+    #
+    #  todo/fix: check if still possible ?? - add an example here how it looks like/works
+
+    values = values.select do |value|
+      if value =~ /^#/  ## start with # treat it as a comment column; e.g. remove it
+        logger.info "   removing column with value »#{value}«"
+        false
+      else
+        true
+      end
+    end
+
+    logger.debug "  values: |»#{values.join('« »')}«|"
+    values
+  end
 
 
 end # class ValuesReader

data/lib/textutils/version.rb

@@ -1,6 +1,7 @@
 
 module TextUtils
 
-  VERSION = '0.7.1'
+  VERSION = '0.8.0'
 
 end   # module TextUtils
+

data/test/test_title_helper.rb

@@ -8,6 +8,7 @@
 
 require 'helper'
 
+
 class TestTitleHelper < MiniTest::Unit::TestCase
 
   def test_title_to_key
@@ -15,7 +16,9 @@ class TestTitleHelper < MiniTest::Unit::TestCase
     txt_io = [
       [ 'São Paulo',   'saopaulo' ],
       [ 'São Gonçalo', 'saogoncalo' ],
-      [ 'Výčepní',     'vycepni' ]
+      [ 'Výčepní',     'vycepni' ],
+      [ 'Bock ‹Damm›', 'bockdamm' ],
+      [ '‹Estrella› ‹Damm› Inedit', 'estrelladamminedit' ]
     ] 
 
     txt_io.each do |txt|

data/test/test_values_reader.rb

@@ -0,0 +1,311 @@
+# encoding: utf-8
+
+###
+#  to run use
+#     ruby -I ./lib -I ./test test/test_helper.rb
+#  or better
+#     rake test
+
+require 'helper'
+
+class TestValuesReader < MiniTest::Unit::TestCase
+
+  def test_escape_comma
+    # note: double espace comma e.g. \\, becomes literal \,
+    txt =<<EOS
+[fuller]
+  Fuller\\, Smith & Turner, 1845
+  The Griffin Brewery // Chiswick Lane South // London, W4 2QB
+  brands: Fuller's
+
+fuller, Fuller\\, Smith & Turner, 1845, The Griffin Brewery // Chiswick Lane South // London\\, W4 2QB
+EOS
+
+    pp txt
+
+    reader = ValuesReader.new( txt )
+
+    i = 0
+    reader.each_line do |attribs, values|
+      i += 1
+
+      puts "attribs:"
+      pp attribs
+      puts "values:"
+      pp values
+
+      if i == 1
+        assert_equal attribs[:key],      'fuller'
+        assert_equal attribs[:title],    'Fuller, Smith & Turner'
+        assert_equal attribs[:grade],    nil
+        assert_equal attribs[:synonyms], nil
+
+        assert_equal values[0],  '1845'
+        assert_equal values[1],  'The Griffin Brewery // Chiswick Lane South // London, W4 2QB'
+        assert_equal values[2],  "brands: Fuller's"
+      elsif i == 2
+        assert_equal attribs[:key],      'fuller'
+        assert_equal attribs[:title],    'Fuller, Smith & Turner'
+        assert_equal attribs[:grade],    nil
+        assert_equal attribs[:synonyms], nil
+
+        assert_equal values[0],  '1845'
+        assert_equal values[1],  'The Griffin Brewery // Chiswick Lane South // London, W4 2QB'
+      else
+        assert_equal true, false   # should not get here
+      end
+    end
+  end # test_escape_comma
+
+
+  def test_mixed
+    txt =<<EOS
+##########
+# Wien Umbgebung
+
+[schwechat]
+  Brauerei Schwechat (Brau Union) **, 1796
+  www.schwechater.at
+  2320 Schwechat // Mautner Markhof-Straße 11
+  brands: Schwechater
+  brau_union   # Part of Brau Union
+
+
+#############
+# Waldviertel
+
+zwettler, Zwettler Brauerei|Privatbrauerei Zwettl **, 1709, www.zwettler.at, 3910 Zwettl // Syrnauer Straße 22-25
+weitra, Weitra Bräu Bierwerkstatt|Brauerei Weitra *, 1321, www.bierwerkstatt.at, 3970 Weitra // Sparkasseplatz 160, zwettler   # Part of Zwettler
+
+#############
+# Weinviertel
+
+[hubertus]
+  Hubertus Bräu *, 1454
+  www.hubertus.at
+  2136 Laa/Thaya // Hubertusgasse 1
+  brands: Hubertus
+
+egger, Privatbrauerei Fritz Egger **, 1978, www.egger-bier.at, 3105 Unterradlberg // Tiroler Straße 18
+EOS
+
+    reader = ValuesReader.new( txt )
+
+    i = 0
+    reader.each_line do |attribs, values|
+      i += 1
+
+      puts "attribs:"
+      pp attribs
+      puts "values:"
+      pp values
+
+      if i == 1
+        assert_equal attribs[:key],      'schwechat'
+        assert_equal attribs[:title],    'Brauerei Schwechat (Brau Union)'
+        assert_equal attribs[:grade],    2
+        assert_equal attribs[:synonyms], nil
+
+        assert_equal values[0],  '1796'
+        assert_equal values[1],  'www.schwechater.at'
+        assert_equal values[2],  '2320 Schwechat // Mautner Markhof-Straße 11'
+        assert_equal values[3],  'brands: Schwechater'
+        assert_equal values[-1], 'brau_union'
+      elsif i == 2
+        assert_equal attribs[:key],      'zwettler'
+        assert_equal attribs[:title],    'Zwettler Brauerei'
+        assert_equal attribs[:grade],    2
+        assert_equal attribs[:synonyms], 'Privatbrauerei Zwettl'
+
+        assert_equal values[0],  '1709'
+        assert_equal values[1],  'www.zwettler.at'
+        assert_equal values[2],  '3910 Zwettl // Syrnauer Straße 22-25'
+      elsif i == 3
+        assert_equal attribs[:key],      'weitra'
+        assert_equal attribs[:title],    'Weitra Bräu Bierwerkstatt'
+        assert_equal attribs[:grade],    3
+        assert_equal attribs[:synonyms], 'Brauerei Weitra'
+
+        assert_equal values[0],  '1321'
+        assert_equal values[1],  'www.bierwerkstatt.at'
+        assert_equal values[2],  '3970 Weitra // Sparkasseplatz 160'
+        assert_equal values[-1], 'zwettler'
+      elsif i == 4
+        assert_equal attribs[:key],      'hubertus'
+        assert_equal attribs[:title],    'Hubertus Bräu'
+        assert_equal attribs[:grade],    3
+        assert_equal attribs[:synonyms], nil
+
+        assert_equal values[0],  '1454'
+        assert_equal values[1],  'www.hubertus.at'
+        assert_equal values[2],  '2136 Laa/Thaya // Hubertusgasse 1'
+        assert_equal values[3],  'brands: Hubertus'
+      elsif i == 5
+        assert_equal attribs[:key],      'egger'
+        assert_equal attribs[:title],    'Privatbrauerei Fritz Egger'
+        assert_equal attribs[:grade],    2
+        assert_equal attribs[:synonyms], nil
+
+        assert_equal values[0],  '1978'
+        assert_equal values[1],  'www.egger-bier.at'
+        assert_equal values[2],  '3105 Unterradlberg // Tiroler Straße 18'
+      else
+        assert_equal true, false   # should not get here
+      end
+    end
+  end # test_mixed
+
+
+  def test_multi_line_records
+    txt =<<EOS
+##########
+# Wien Umbgebung
+
+[schwechat]
+  Brauerei Schwechat (Brau Union) **, 1796
+  www.schwechater.at
+  2320 Schwechat // Mautner Markhof-Straße 11
+  brands: Schwechater
+  brau_union   # Part of Brau Union
+
+
+#############
+# Waldviertel
+
+[zwettler]
+  Zwettler Brauerei|Privatbrauerei Zwettl **, 1709
+  www.zwettler.at
+  3910 Zwettl // Syrnauer Straße 22-25
+  brands: Zwettler
+EOS
+
+    reader = ValuesReader.new( txt )
+
+    i = 0
+    reader.each_line do |attribs, values|
+      i += 1
+
+      puts "attribs:"
+      pp attribs
+      puts "values:"
+      pp values
+
+      if i == 1
+        assert_equal attribs[:key],      'schwechat'
+        assert_equal attribs[:title],    'Brauerei Schwechat (Brau Union)'
+        assert_equal attribs[:grade],    2
+        assert_equal attribs[:synonyms], nil
+
+        assert_equal values[0],  '1796'
+        assert_equal values[1],  'www.schwechater.at'
+        assert_equal values[2],  '2320 Schwechat // Mautner Markhof-Straße 11'
+        assert_equal values[3],  'brands: Schwechater'
+        assert_equal values[-1], 'brau_union'
+      elsif i == 2
+        assert_equal attribs[:key],      'zwettler'
+        assert_equal attribs[:title],    'Zwettler Brauerei'
+        assert_equal attribs[:grade],    2
+        assert_equal attribs[:synonyms], 'Privatbrauerei Zwettl'
+
+        assert_equal values[0],  '1709'
+        assert_equal values[1],  'www.zwettler.at'
+        assert_equal values[2],  '3910 Zwettl // Syrnauer Straße 22-25'
+        assert_equal values[3],  'brands: Zwettler'
+      else
+        assert_equal true, false   # should not get here
+      end
+    end
+  end  # test_multi_line_records
+
+
+  def test_classic_csv_records
+
+    txt =<<EOS
+arsenal,     Arsenal|Arsenal FC|FC Arsenal,             ARS, city:london
+manunited,   Manchester United|Man Utd|Manchester U.,   MUN, city:manchester
+liverpool,   Liverpool|Liverpool FC|FC Liverpool,       LIV, city:liverpool
+EOS
+
+    reader = ValuesReader.new( txt )
+
+    i = 0
+    reader.each_line do |attribs, values|
+      i += 1
+
+      puts "attribs:"
+      pp attribs
+      puts "values:"
+      pp values
+
+      if i == 1
+        assert_equal attribs[:key],      'arsenal'
+        assert_equal attribs[:title],    'Arsenal'
+        assert_equal attribs[:synonyms], 'Arsenal FC|FC Arsenal'
+
+        assert_equal values[0], 'ARS'
+        assert_equal values[1], 'city:london'
+      elsif i == 2
+      elsif i == 3
+      else
+        assert_equal true, false   # should not get here
+      end
+    end
+  end  #  test_classic_csv_records
+
+
+  def test_autogen_keys
+    txt =<<EOS
+Ottakringer Helles,                  5.2 %, 11.8°
+Ottakringer Gold Fassl Spezial,      5.6 %, 12.7°
+Ottakringer (Gold Fassl) Pils,       4.6 %, 11.2°
+Ottakringer (Gold Fassl) Pur {Bio},  5.2 %, 11.8°, bio
+EOS
+
+    reader = ValuesReader.new( txt )
+
+    i = 0
+    reader.each_line do |attribs, values|
+      i += 1
+
+      puts "attribs:"
+      pp attribs
+      puts "values:"
+      pp values
+
+      if i == 1
+        assert_equal attribs[:key],      'ottakringerhelles'
+        assert_equal attribs[:title],    'Ottakringer Helles'
+        assert_equal attribs[:synonyms], nil
+
+        assert_equal values[0], '5.2 %'
+        assert_equal values[1], '11.8°'
+      elsif i == 2
+        assert_equal attribs[:key],      'ottakringergoldfasslspezial'
+        assert_equal attribs[:title],    'Ottakringer Gold Fassl Spezial'
+        assert_equal attribs[:synonyms], nil
+
+        assert_equal values[0], '5.6 %'
+        assert_equal values[1], '12.7°'
+      elsif i == 3
+        assert_equal attribs[:key],      'ottakringerpils'
+        assert_equal attribs[:title],    'Ottakringer (Gold Fassl) Pils'
+        assert_equal attribs[:synonyms], nil
+
+        assert_equal values[0], '4.6 %'
+        assert_equal values[1], '11.2°'
+      elsif i == 4
+        assert_equal attribs[:key],      'ottakringerpur'
+        assert_equal attribs[:title],    'Ottakringer (Gold Fassl) Pur {Bio}'
+        assert_equal attribs[:synonyms], nil
+
+        assert_equal values[0], '5.2 %'
+        assert_equal values[1], '11.8°'
+        assert_equal values[-1], 'bio'
+      else
+        assert_equal true, false   # should not get here
+      end
+    end
+  end # test_autogen_keys
+
+
+end # class TestValuesReader

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: textutils
 version: !ruby/object:Gem::Version
-  version: 0.7.1
+  version: 0.8.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-12-25 00:00:00.000000000 Z
+date: 2014-01-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: logutils
-  requirement: &21849324 !ruby/object:Gem::Requirement
+  requirement: &3086976 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -21,10 +21,10 @@ dependencies:
         version: '0.5'
   type: :runtime
   prerelease: false
-  version_requirements: *21849324
+  version_requirements: *3086976
 - !ruby/object:Gem::Dependency
   name: rdoc
-  requirement: &21848640 !ruby/object:Gem::Requirement
+  requirement: &3085764 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -32,10 +32,10 @@ dependencies:
         version: '4.0'
   type: :development
   prerelease: false
-  version_requirements: *21848640
+  version_requirements: *3085764
 - !ruby/object:Gem::Dependency
   name: hoe
-  requirement: &21848040 !ruby/object:Gem::Requirement
+  requirement: &3082920 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -43,17 +43,19 @@ dependencies:
         version: '3.7'
   type: :development
   prerelease: false
-  version_requirements: *21848040
+  version_requirements: *3082920
 description: textutils - Text Filters, Helpers, Readers and More
 email: ruby-talk@ruby-lang.org
 executables: []
 extensions: []
 extra_rdoc_files:
+- History.md
 - Manifest.txt
+- README.md
 files:
-- History.markdown
+- History.md
 - Manifest.txt
-- README.markdown
+- README.md
 - Rakefile
 - lib/textutils.rb
 - lib/textutils/classifier.rb
@@ -82,6 +84,7 @@ files:
 - test/test_hypertext_helper.rb
 - test/test_title_helper.rb
 - test/test_unicode_helper.rb
+- test/test_values_reader.rb
 - .gemtest
 homepage: https://github.com/rubylibs/textutils
 licenses:
@@ -89,7 +92,7 @@ licenses:
 post_install_message: 
 rdoc_options:
 - --main
-- README.markdown
+- README.md
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
@@ -114,3 +117,4 @@ test_files:
 - test/test_hypertext_helper.rb
 - test/test_title_helper.rb
 - test/test_unicode_helper.rb
+- test/test_values_reader.rb