food_ingredient_parser 1.1.4 → 1.1.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 64b65447c4e16dadb986f1422cc02449e7050858
-  data.tar.gz: 94842b54aa5701e384c6fc3e35a3b8d03ca9b978
+SHA256:
+  metadata.gz: 1e83f2b90f83d4cb0deb193140dcce6f4ee1700a80c781c95b7fa09219da9f69
+  data.tar.gz: '0929b958e93cf8e61e54b5e268ad32135aa45e87d1c163ae912790de55a85e28'
 SHA512:
-  metadata.gz: b91f77676d5edab883e89701f9b1a2e6659ad8ef655080314d0f23cedf9afc79b20cb1e3ae93504e17cda5dbd710501fb00b9b4cb581e2020d11671ca094b696
-  data.tar.gz: c2afb010c5b967dc411f52645231fb36465346aad0f937461bf1b51fa2e198afe60973570abff2d35cbc5f8b2c3d2fe4151ee90b70bc4e3ad33513648ab2e03c
+  metadata.gz: 929fd7057be9e1f35ec1db55e08bad1078d8bc1f977b07b25c26f3f0ce0919e0cb82ca4379e050067b20ab5cee760fb10c2d267d60fc7555d18af1e8ae9ca9e9
+  data.tar.gz: 4873942e33ad823fbf84391cc70c4f4760cf0d93cceced307814d3abf73f5e91af8529fcfa048345b0a896dd967deac729d9051ab7e89b3c4174c8ee42f9f61b

data/bin/food_ingredient_parser

@@ -41,8 +41,10 @@ def parse_single(s, parsed=nil, parser:, verbosity: 1, print: nil, escape: false
   if parsed
     puts(parsed.inspect) if verbosity > 1
     pp(parsed.to_h, color: color) if verbosity > 0
+    return true
   else
     puts "(no result: #{parser.parser.failure_reason})" if verbosity > 0
+    return false
   end
 end
 
@@ -63,6 +65,7 @@ def parse_file(path, parser:, verbosity: 1, print: nil, escape: false, color: fa
   pct_parsed   = 100.0 * count_parsed / (count_parsed + count_noresult)
   pct_noresult = 100.0 * count_noresult / (count_parsed + count_noresult)
   puts "parsed #{colorize(color && "1;32", count_parsed)} (#{pct_parsed.round(1)}%), no result #{colorize(color && "1;31", count_noresult)} (#{pct_noresult.round(1)}%)"
+  return count_noresult
 end
 
 verbosity = 1
@@ -108,8 +111,10 @@ if strings.any? || files.any?
     STDERR.puts("Please specify one of the known parsers: #{PARSERS.keys.join(", ")}.")
     exit(1)
   end
-  strings.each {|s| parse_single(s, parser: parser, verbosity: verbosity, print: print, escape: escape, color: color) }
-  files.each   {|f| parse_file(f, parser: parser, verbosity: verbosity, print: print, escape: escape, color: color) }
+  success = true
+  strings.each {|s| success &= parse_single(s, parser: parser, verbosity: verbosity, print: print, escape: escape, color: color) }
+  files.each   {|f| success &= parse_file(f, parser: parser, verbosity: verbosity, print: print, escape: escape, color: color) == 0 }
+  success or exit(1)
 else
   STDERR.puts("Please specify one or more --file or --string arguments (see --help).")
 end

data/lib/food_ingredient_parser/cleaner.rb

@@ -2,13 +2,14 @@ module FoodIngredientParser
   module Cleaner
 
     def self.clean(s)
-      s.gsub!("\u00ad", "")             # strip soft hyphen
-      s.gsub!("\u0092", "'")            # windows-1252 apostrophe - https://stackoverflow.com/a/15564279/2866660
-      s.gsub!("aÄs", "aïs")             # encoding issue for maïs
-      s.gsub!("ï", "ï")                # encoding issue
-      s.gsub!("ë", "ë")                # encoding issue
-      s.gsub!(/\A\s*"(.*)"\s*\z/, '\1') # enclosing double quotation marks
-      s.gsub!(/\A\s*'(.*)'\s*\z/, '\1') # enclosing single quotation marks
+      s.gsub!(/(_x005f_|_)x000d_/i, "\n") # fix sometimes encoding for newline
+      s.gsub!("\u00ad", "")               # strip soft hyphen
+      s.gsub!("\u0092", "'")              # windows-1252 apostrophe - https://stackoverflow.com/a/15564279/2866660
+      s.gsub!("‚", ",")                   # normalize unicode comma
+      s.gsub!("aÄs", "aïs")               # encoding issue for maïs
+      s.gsub!("ï", "ï")                  # encoding issue
+      s.gsub!("ë", "ë")                  # encoding issue
+      s.gsub!(/\A\s*(["']+)(.*)\1\s*\z/, '\2') # enclosing quotation marks
       s
     end
 

data/lib/food_ingredient_parser/loose/scanner.rb

@@ -4,19 +4,23 @@ module FoodIngredientParser::Loose
   class Scanner
 
     SEP_CHARS  = "|;,.".freeze
-    MARK_CHARS = "¹²³⁴⁵ᵃᵇᶜᵈᵉᶠᵍªº⁽⁾†‡•°#^*".freeze
+    MARK_CHARS = "¹²³⁴⁵ᵃᵇᶜᵈᵉᶠᵍªº⁽⁾†‡⁺•°▪◊#^˄*~".freeze
     PREFIX_RE  = /\A\s*(ingredients|contains|ingred[iï][eë]nt(en)?(declaratie)?|bevat|dit zit er\s?in|samenstelling|zutaten)\b\s*[:;.]?\s*/i.freeze
-    NOTE_RE    = /\A\b(dit product kan\b|deze verpakking kan\b|kan sporen\b.*?\bbevatten\b|voor allergenen\b|allergenen\b|E\s*=|gemaakt in\b|geproduceerd in\b|bevat mogelijk\b|kijk voor meer\b|allergie-info|in de fabriek\b|in dit bedrijf\b|voor [0-9,.]+ (g\.?|gr\.?|ram|ml).*\bis [0-9,.]+ (g\.?|gr\.?|ram|ml).*\bgebruikt\b)/i.freeze
+    NOTE_RE    = /\A\b(dit product kan\b|deze verpakking kan\b|kan sporen\b.*?\bbevatten\b|voor allergenen\b|allergenen\b|allergie[- ]informatie(\s*:|\b)|E\s*=|gemaakt in\b|geproduceerd in\b|bevat mogelijk\b|kijk voor meer\b|allergie-info|in de fabriek\b|in dit bedrijf\b|voor [0-9,.]+ (g\.?|gr\.?|ram|ml).*\bis [0-9,.]+ (g\.?|gr\.?|ram|ml).*\bgebruikt\b)/i.freeze
     # Keep in sync with +abbrev+ in the +Common+ grammar, plus relevant ones from the +Amount+ grammar.
     ABBREV_RE  = Regexp.union(
       /\A(
         N°\b |
         °C\b |
         (ijzer|chroom|koper)\s*\(I+\)\s*[[:alnum:]]+\b |
-        L\(\+\)-[[:alnum:]]+\b |
+        L\(\+\)[ -][[:alnum:]]+\b |
+        L\.\s+rhamnosus\b | L\.\s+acidophilus\b | L\.\s+casei\b | B\.\s+lactis | A\.\s+oryzae |
+        S\.\s+thermophilus\b | L\.\sbulgaricus\b |
+        T\.\s*aestivum\b(\s+vitt\.)? |
+        nucifera\s+L\. |
         type\s+"\d+" |
-        L\.\s+rhamnosus\b | L\.\s+acidophilus\b | L\.\s+casei\b | B\.\s+lactis | A\.\s+oryzae
-        E-e?\d{3}[a-z]?\s*\(i+\)
+        E[- ]?\d{3}[a-z]?\s*\([iv]+\) |
+        www\.[-_\/:%.A-Za-z0-9]+
       )/xi,
       *%w[
         a.o.p b.g.a b.o.b c.a c.i d.e d.m.v d.o.c d.o.p d.s e.a e.g e.u f.i.l f.o.s i.a

data/lib/food_ingredient_parser/loose/transform/split_e_numbers.rb

@@ -8,7 +8,7 @@ module FoodIngredientParser::Loose
       # @note mark and amount is lost, this is not expected on e-numbers
 
       SPLIT_RE  = /\s*-\s*/.freeze
-      SINGLE_RE = /E-?\d{3}[a-z]?(?:\s*\(i+\))?/i.freeze
+      SINGLE_RE = /E-?\d{3}[a-z]?(?:\s*\([iv]+\))?/i.freeze
       MATCH_RE  = /\A\s*(#{SINGLE_RE})(?:#{SPLIT_RE}(#{SINGLE_RE}))+\s*\z/i.freeze
 
       def self.transform!(node)

data/lib/food_ingredient_parser/strict/grammar/amount.treetop

@@ -21,23 +21,30 @@ module FoodIngredientParser::Strict::Grammar
       ) ws* )?
       amount_simple_quantity
       ( ws+ (
-        'of'i / 'or less of'i / 'or more of'i /
-        'minimaal'i / 'minimum'i / 'van het uitlekgewicht'i / 'van het geheel'i /
+        'of a'i / 'of'i / 'or less of'i / 'or more of'i /
+        'van een'i / 'minimaal'i / 'minimum'i / 'van het uitlekgewicht'i / 'van het geheel'i /
         'min.'i / 'min'i / 'max.'i / 'max'i
       ) )?
     end
 
     rule amount_simple_quantity
-      amount_simple_number ( ws* amount_simple_unit? ws* dash ws* amount_simple_number )? ws* amount_simple_unit
+      amount_simple_number ( ws* amount_simple_unit? ws* dash ws* amount_simple_number )? ( ws* amount_simple_unit )?
     end
 
     rule amount_simple_number
-      ( [±∓~∼∽≂≃≈≲≤<>≥≳] ws* )? number
+      ( amount_simple_comparator ws* )? number
+    end
+
+    rule amount_simple_comparator
+      '=' ws* [<>] /
+      [<>] ws* ( '=' / 'of gelijk aan'i !char / 'or equal to'i !char ) /
+      [±∓~∼∽≂≃≈≲≤<>≥≳] / '+/-' / '-/+'
     end
 
     rule amount_simple_unit
-      ( percent / ( ( 'procent' / 'percent' / 'gram'i / 'ml'i / 'mg'i / 'gr'i / 'g'i ) !char ) )
+      ( percent / ( ( 'procent' / 'percent' / 'gram'i / 'ml'i / 'mg'i / 'gr'i / 'g'i / 'ppm'i ) !char ) )
       ( ws 'vol'i ( !char / '.' ) )?
+      ( ws* '℮' )?
     end
   end
 end

data/lib/food_ingredient_parser/strict/grammar/common.treetop

@@ -12,15 +12,20 @@ module FoodIngredientParser::Strict::Grammar
     rule char
       !mark [[:alnum:]] /
       fraction /
-      [-/\`'´’+=_{}&] /
-      [®™] /
-      [¿?] /                         # weird characters turning up in names (e.g. encoding issues)
+      [-/\`'"´‘’+=_{}&] /
+      [®©™♣] /
+      [¿?¯] /                        # weird characters turning up in names (e.g. encoding issues)
       [₁₂₃₄₅₆₇₈₉]                    # can occur with vitamins
     end
 
     rule mark
       # mark referencing a footnote
-      [¹²³⁴⁵ᵃᵇᶜᵈᵉᶠᵍªº] '⁾'? / '⁽' [¹²³⁴⁵ᵃᵇᶜᵈᵉᶠᵍªº] '⁾' / [†‡•°#^] / '*'+ / '(' ws* ( [†‡•°#^] / '*'+ ) ws* ')'
+      [¹²³⁴⁵ᵃᵇᶜᵈᵉᶠᵍªº] '⁾'? /
+      '⁽' [¹²³⁴⁵ᵃᵇᶜᵈᵉᶠᵍªº] '⁾' /
+      [˄^] digit /
+      [†‡⁺•°▪◊#˄^~˛] /
+      '*'+ /
+      '(' ws* ( [†‡⁺•°▪◊#˄^~˛] / '*'+ ) ws* ')'
     end
 
     rule digit
@@ -28,7 +33,8 @@ module FoodIngredientParser::Strict::Grammar
     end
 
     rule fraction
-      [½⅓⅔¼¾⅕⅖⅗⅘⅙⅚⅐⅛⅜⅝⅞⅑⅒]
+      [½⅓⅔¼¾⅕⅖⅗⅘⅙⅚⅐⅛⅜⅝⅞⅑⅒] /
+      digit+ '/' digit+
     end
 
     rule percent
@@ -53,7 +59,21 @@ module FoodIngredientParser::Strict::Grammar
 
     rule e_number
       ( 'E'i '-'? [0-9] [0-9] [0-9] [[:alpha:]]? )
-      ![[:alnum:]] / ( ws* '(' 'i'i+ ')' ) # e.g. "E450 (iii)"
+      ( ( ws* '(' [iIvV]+ ')' ) / ![[:alnum:]] ) # e.g. "E450 (iii)"
+    end
+
+    rule chem_systematic_name
+      ( chem_systematic_name_num dash ) ( chem_systematic_name_word dash chem_systematic_name_num dash ws? )* chem_systematic_name_word /
+      ( chem_systematic_name_word dash chem_systematic_name_num dash ws? )+ chem_systematic_name_word
+    end
+
+    rule chem_systematic_name_word
+      [A-Za-z]+ ( dash [A-Za-z]+ dash [A-Za-z]+ )*
+    end
+
+    rule chem_systematic_name_num
+      digit+ [RH] /
+      digit+ ( ',' digit+ )* '\''?
     end
 
     rule abbrev
@@ -110,12 +130,14 @@ module FoodIngredientParser::Strict::Grammar
         'w.o'i /
         'w.v'i /
         # not auto-generated additions
+        'nr.'i /
         'vit'i /   # vitamin
         'denat'i / # denaturated
         'alc'i /   # alcohol
         'vol'i /   # volume
         'conc'i /  # concentration
-        'subsp'i   # subspecies
+        'subsp'i / # subspecies
+        'www.'i [-_\/:%.A-Za-z0-9]+
       )
       '.'? ![[:alpha:]]
     end
@@ -126,10 +148,14 @@ module FoodIngredientParser::Strict::Grammar
         'N°'i /
         '°C'i /
         ( 'ijzer'i / 'chroom'i / 'koper'i ) ws* '(' 'I'i+ ')' ws* [[:alnum:]]+ /
-        'L(+)-' [[:alnum:]]+ /
+        'L(+)' ('-' / ws) [[:alnum:]]+ /
         'L.' ws+ 'rhamnosus'i / 'L.' ws+ 'acidophilus'i / 'L.' ws+ 'casei' / 'B.'i ws+ 'lactis'i / 'A.'i ws+ 'oryzae'i /
+        'S.' ws+ 'thermophilus'i / 'L.' ws+ 'bulgaricus'i /
+        'T.' ws* 'aestivum'i (ws+ 'vitt.'i)? /
+        'nucifera' ws+ 'L.'i /
         'type'i ws+ '"' [0-9]+ '"' /
-        e_number
+        e_number /
+        chem_systematic_name
       ) ![[:alpha:]]
     end
   end

data/lib/food_ingredient_parser/strict/grammar/root.treetop

@@ -40,7 +40,7 @@ module FoodIngredientParser::Strict::Grammar
     end
 
     rule root_mark_sentences_in_list
-      ( ( ws* [,.;] / ws ) ws* root_mark_sentence_in_list )+
+      ( ( ws* [,.;] / ws )+ root_mark_sentence_in_list )+
     end
 
     rule root_mark_sentence_in_list

data/lib/food_ingredient_parser/version.rb

@@ -1,4 +1,4 @@
 module FoodIngredientParser
-  VERSION      = '1.1.4'
-  VERSION_DATE = '2018-10-22'
+  VERSION      = '1.1.9'
+  VERSION_DATE = '2021-01-12'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: food_ingredient_parser
 version: !ruby/object:Gem::Version
-  version: 1.1.4
+  version: 1.1.9
 platform: ruby
 authors:
 - wvengen
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-10-22 00:00:00.000000000 Z
+date: 2021-01-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: treetop
@@ -87,8 +87,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.6.13
+rubygems_version: 3.0.3
 signing_key: 
 specification_version: 4
 summary: Parser for ingredient lists found on food products.