food_ingredient_parser 1.1.4 → 1.1.5

Sign up to get free protection for your applications and to get access to all the features.
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA1:
3
- metadata.gz: 64b65447c4e16dadb986f1422cc02449e7050858
4
- data.tar.gz: 94842b54aa5701e384c6fc3e35a3b8d03ca9b978
3
+ metadata.gz: 8c80d036dbee183ed2fd1a8cc4e513e54318d142
4
+ data.tar.gz: 6cfcd29eacb9e99a9be9a66a90446f47f714ae4b
5
5
  SHA512:
6
- metadata.gz: b91f77676d5edab883e89701f9b1a2e6659ad8ef655080314d0f23cedf9afc79b20cb1e3ae93504e17cda5dbd710501fb00b9b4cb581e2020d11671ca094b696
7
- data.tar.gz: c2afb010c5b967dc411f52645231fb36465346aad0f937461bf1b51fa2e198afe60973570abff2d35cbc5f8b2c3d2fe4151ee90b70bc4e3ad33513648ab2e03c
6
+ metadata.gz: 75b1f91e5db6bcfcc24ad8eabe16b541663e5e344604c31b884ab1a5633c95dc045cdee2d384f5434f5143b778659cecd69917b9adb16e25341978380e486bcc
7
+ data.tar.gz: 7254cca971a558bda2ae6e996cc4d121fc5138f09d67c847bb44eec87421aeea39bf18a771137eb3b0b2bb734bed058a1d2347f815b9edc1b23e0b069d83a381
@@ -4,19 +4,22 @@ module FoodIngredientParser::Loose
4
4
  class Scanner
5
5
 
6
6
  SEP_CHARS = "|;,.".freeze
7
- MARK_CHARS = "¹²³⁴⁵ᵃᵇᶜᵈᵉᶠᵍªº⁽⁾†‡•°#^*".freeze
7
+ MARK_CHARS = "¹²³⁴⁵ᵃᵇᶜᵈᵉᶠᵍªº⁽⁾†‡•°▪◊#^*".freeze
8
8
  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
9
- 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
9
+ 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
10
10
  # Keep in sync with +abbrev+ in the +Common+ grammar, plus relevant ones from the +Amount+ grammar.
11
11
  ABBREV_RE = Regexp.union(
12
12
  /\A(
13
13
  N°\b |
14
14
  °C\b |
15
15
  (ijzer|chroom|koper)\s*\(I+\)\s*[[:alnum:]]+\b |
16
- L\(\+\)-[[:alnum:]]+\b |
16
+ L\(\+\)[ -][[:alnum:]]+\b |
17
+ L\.\s+rhamnosus\b | L\.\s+acidophilus\b | L\.\s+casei\b | B\.\s+lactis | A\.\s+oryzae |
18
+ S\.\s+thermophilus\b | L\.\sbulgaricus\b |
19
+ T\.\s*aestivum\b(\s+vitt\.)? |
17
20
  type\s+"\d+" |
18
- L\.\s+rhamnosus\b | L\.\s+acidophilus\b | L\.\s+casei\b | B\.\s+lactis | A\.\s+oryzae
19
- E-e?\d{3}[a-z]?\s*\(i+\)
21
+ E-e?\d{3}[a-z]?\s*\(i+\) |
22
+ www\.[-_\/:%.A-Za-z0-9]+
20
23
  )/xi,
21
24
  *%w[
22
25
  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
@@ -38,6 +38,7 @@ module FoodIngredientParser::Strict::Grammar
38
38
  rule amount_simple_unit
39
39
  ( percent / ( ( 'procent' / 'percent' / 'gram'i / 'ml'i / 'mg'i / 'gr'i / 'g'i ) !char ) )
40
40
  ( ws 'vol'i ( !char / '.' ) )?
41
+ ( ws* '℮' )?
41
42
  end
42
43
  end
43
44
  end
@@ -12,7 +12,7 @@ module FoodIngredientParser::Strict::Grammar
12
12
  rule char
13
13
  !mark [[:alnum:]] /
14
14
  fraction /
15
- [-/\`'´’+=_{}&] /
15
+ [-/\`'´‘’+=_{}&] /
16
16
  [®™] /
17
17
  [¿?] / # weird characters turning up in names (e.g. encoding issues)
18
18
  [₁₂₃₄₅₆₇₈₉] # can occur with vitamins
@@ -20,7 +20,7 @@ module FoodIngredientParser::Strict::Grammar
20
20
 
21
21
  rule mark
22
22
  # mark referencing a footnote
23
- [¹²³⁴⁵ᵃᵇᶜᵈᵉᶠᵍªº] '⁾'? / '⁽' [¹²³⁴⁵ᵃᵇᶜᵈᵉᶠᵍªº] '⁾' / [†‡•°#^] / '*'+ / '(' ws* ( [†‡•°#^] / '*'+ ) ws* ')'
23
+ [¹²³⁴⁵ᵃᵇᶜᵈᵉᶠᵍªº] '⁾'? / '⁽' [¹²³⁴⁵ᵃᵇᶜᵈᵉᶠᵍªº] '⁾' / [†‡•°▪◊#^] / '*'+ / '(' ws* ( [†‡•°▪◊#^] / '*'+ ) ws* ')'
24
24
  end
25
25
 
26
26
  rule digit
@@ -115,7 +115,8 @@ module FoodIngredientParser::Strict::Grammar
115
115
  'alc'i / # alcohol
116
116
  'vol'i / # volume
117
117
  'conc'i / # concentration
118
- 'subsp'i # subspecies
118
+ 'subsp'i / # subspecies
119
+ 'www.'i [-_\/:%.A-Za-z0-9]+
119
120
  )
120
121
  '.'? ![[:alpha:]]
121
122
  end
@@ -126,8 +127,10 @@ module FoodIngredientParser::Strict::Grammar
126
127
  'N°'i /
127
128
  '°C'i /
128
129
  ( 'ijzer'i / 'chroom'i / 'koper'i ) ws* '(' 'I'i+ ')' ws* [[:alnum:]]+ /
129
- 'L(+)-' [[:alnum:]]+ /
130
+ 'L(+)' ('-' / ws) [[:alnum:]]+ /
130
131
  'L.' ws+ 'rhamnosus'i / 'L.' ws+ 'acidophilus'i / 'L.' ws+ 'casei' / 'B.'i ws+ 'lactis'i / 'A.'i ws+ 'oryzae'i /
132
+ 'S.' ws+ 'thermophilus'i / 'L.' ws+ 'bulgaricus'i /
133
+ 'T.' ws* 'aestivum'i (ws+ 'vitt.'i)? /
131
134
  'type'i ws+ '"' [0-9]+ '"' /
132
135
  e_number
133
136
  ) ![[:alpha:]]
@@ -1,4 +1,4 @@
1
1
  module FoodIngredientParser
2
- VERSION = '1.1.4'
3
- VERSION_DATE = '2018-10-22'
2
+ VERSION = '1.1.5'
3
+ VERSION_DATE = '2019-11-14'
4
4
  end
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: food_ingredient_parser
3
3
  version: !ruby/object:Gem::Version
4
- version: 1.1.4
4
+ version: 1.1.5
5
5
  platform: ruby
6
6
  authors:
7
7
  - wvengen
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2018-10-22 00:00:00.000000000 Z
11
+ date: 2019-11-14 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: treetop