food_ingredient_parser 1.0.0.pre.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/LICENSE +22 -0
- data/README.md +115 -0
- data/bin/food_ingredient_parser +107 -0
- data/food_ingredient_parser.gemspec +29 -0
- data/lib/food_ingredient_parser/grammar/amount.treetop +30 -0
- data/lib/food_ingredient_parser/grammar/common.treetop +150 -0
- data/lib/food_ingredient_parser/grammar/ingredient.treetop +12 -0
- data/lib/food_ingredient_parser/grammar/ingredient_coloned.treetop +41 -0
- data/lib/food_ingredient_parser/grammar/ingredient_nested.treetop +28 -0
- data/lib/food_ingredient_parser/grammar/ingredient_simple.treetop +21 -0
- data/lib/food_ingredient_parser/grammar/list.treetop +14 -0
- data/lib/food_ingredient_parser/grammar/list_coloned.treetop +23 -0
- data/lib/food_ingredient_parser/grammar/list_newlined.treetop +16 -0
- data/lib/food_ingredient_parser/grammar/root.treetop +51 -0
- data/lib/food_ingredient_parser/grammar.rb +16 -0
- data/lib/food_ingredient_parser/nodes.rb +69 -0
- data/lib/food_ingredient_parser/parser.rb +34 -0
- data/lib/food_ingredient_parser/version.rb +3 -0
- data/lib/food_ingredient_parser.rb +2 -0
- metadata +85 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 7d20d204e60d22f23f7aa3a039450629c8f4c729
|
4
|
+
data.tar.gz: 127801cb5a00b81ca6abf244d92bfebb39ddde28
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 3a79c07b4f193fcfbbd08f62fdd18407fc034ea036d5b4b5eb3278e449e337e1ee5e0ad5f468bab5f8e948746e99a6bcf5d686e13277b39dafb9c3b11d3ca531
|
7
|
+
data.tar.gz: 95c224f63934e3c601b62d0db9a7d8dc6070fe008816298e3e81f435751012d1bbf66d6270259c4f6e9252a9df6e6d0cf15081e8020e99853c0abb7af55b1a96
|
data/LICENSE
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
MIT License
|
2
|
+
|
3
|
+
Copyright (c) 2018 Questionmark
|
4
|
+
Copyright (c) 2018 wvengen
|
5
|
+
|
6
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
7
|
+
of this software and associated documentation files (the "Software"), to deal
|
8
|
+
in the Software without restriction, including without limitation the rights
|
9
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
10
|
+
copies of the Software, and to permit persons to whom the Software is
|
11
|
+
furnished to do so, subject to the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be included in all
|
14
|
+
copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
17
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
18
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
19
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
20
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
21
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
22
|
+
SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,115 @@
|
|
1
|
+
# Food ingredient parser
|
2
|
+
|
3
|
+
Ingredients are listed on food products in various ways. This [Ruby](https://www.ruby-lang.org/)
|
4
|
+
gem and program parses the ingredient text and returns a structured representation.
|
5
|
+
|
6
|
+
## Installation
|
7
|
+
|
8
|
+
```
|
9
|
+
gem install food_ingredient_parser
|
10
|
+
```
|
11
|
+
|
12
|
+
This will also install the dependency [treetop](http://cjheath.github.io/treetop).
|
13
|
+
If you want colored output for the test program, also install [pry](http://pryrepl.org/): `gem install pry`.
|
14
|
+
|
15
|
+
## Example
|
16
|
+
|
17
|
+
```ruby
|
18
|
+
require 'food_ingredient_parser'
|
19
|
+
|
20
|
+
s = "Water* 60%, suiker 30%, voedingszuren: citroenzuur, appelzuur, zuurteregelaar: E576/E577, " \
|
21
|
+
+ "natuurlijke citroen-limoen aroma's 0,2%, zoetstof: steviolglycosiden, * = Biologisch. " \
|
22
|
+
+ "E = door de E.U. goedgekeurde toevoeging."
|
23
|
+
parser = FoodIngredientParser::Parser.new
|
24
|
+
puts parser.parse(s).to_h.inspect
|
25
|
+
```
|
26
|
+
Results in
|
27
|
+
```
|
28
|
+
{
|
29
|
+
:contains=>[
|
30
|
+
{:name=>"Water", :amount=>"60%", :mark=>"*"},
|
31
|
+
{:name=>"suiker", :amount=>"30%"},
|
32
|
+
{:name=>"voedingszuren", :contains=>[
|
33
|
+
{:name=>"citroenzuur"}
|
34
|
+
]},
|
35
|
+
{:name=>"appelzuur"},
|
36
|
+
{:name=>"zuurteregelaar", :contains=>[
|
37
|
+
{:name=>"E576"},
|
38
|
+
{:name=>"E577"}
|
39
|
+
]},
|
40
|
+
{:name=>"natuurlijke citroen-limoen aroma's", :amount=>"0,2%"},
|
41
|
+
{:name=>"zoetstof", :contains=>[
|
42
|
+
{:name=>"steviolglycosiden"}
|
43
|
+
]}
|
44
|
+
],
|
45
|
+
:notes=>[
|
46
|
+
"* = Biologisch",
|
47
|
+
"E = door de E.U. goedgekeurde toevoeging"
|
48
|
+
]
|
49
|
+
}
|
50
|
+
```
|
51
|
+
|
52
|
+
## Test tool
|
53
|
+
|
54
|
+
The executable `food_ingredient_parser` is available after installing the gem. If you're
|
55
|
+
running this from the source tree, use `bin/food_ingredient_parser` instead.
|
56
|
+
|
57
|
+
```
|
58
|
+
$ food_ingredient_parser -h
|
59
|
+
Usage: food_ingredient_parser [options] --file|-f <filename>
|
60
|
+
food_ingredient_parser [options] --string|-s <ingredients>
|
61
|
+
|
62
|
+
-f, --file FILE Parse all lines of the file as ingredient lists.
|
63
|
+
-s, --string INGREDIENTS Parse specified ingredient list.
|
64
|
+
-q, --[no-]quiet Only show summary.
|
65
|
+
-p, --parsed Only show lines that were successfully parsed.
|
66
|
+
-e, --escape Escape newlines
|
67
|
+
-c, --[no-]color Use color
|
68
|
+
-n, --noresult Only show lines that had no result.
|
69
|
+
-v, --[no-]verbose Show more data (parsed tree).
|
70
|
+
--version Show program version.
|
71
|
+
-h, --help Show this help
|
72
|
+
|
73
|
+
$ food_ingredient_parser -v -s "tomato"
|
74
|
+
"tomato"
|
75
|
+
RootNode+Root3 offset=0, "tomato" (contains,notes):
|
76
|
+
SyntaxNode offset=0, ""
|
77
|
+
SyntaxNode offset=0, ""
|
78
|
+
SyntaxNode offset=0, ""
|
79
|
+
ListNode+List13 offset=0, "tomato" (contains):
|
80
|
+
SyntaxNode+List12 offset=0, "tomato" (ingredient):
|
81
|
+
SyntaxNode+Ingredient0 offset=0, "tomato":
|
82
|
+
SyntaxNode offset=0, ""
|
83
|
+
IngredientNode+IngredientSimpleWithAmount3 offset=0, "tomato" (ing):
|
84
|
+
IngredientNode+IngredientSimple5 offset=0, "tomato" (name):
|
85
|
+
SyntaxNode+IngredientSimple4 offset=0, "tomato" (word):
|
86
|
+
SyntaxNode offset=0, "tomato":
|
87
|
+
SyntaxNode offset=0, "t"
|
88
|
+
SyntaxNode offset=1, "o"
|
89
|
+
SyntaxNode offset=2, "m"
|
90
|
+
SyntaxNode offset=3, "a"
|
91
|
+
SyntaxNode offset=4, "t"
|
92
|
+
SyntaxNode offset=5, "o"
|
93
|
+
SyntaxNode offset=6, ""
|
94
|
+
SyntaxNode offset=6, ""
|
95
|
+
SyntaxNode offset=6, ""
|
96
|
+
SyntaxNode+Root2 offset=6, "":
|
97
|
+
SyntaxNode offset=6, ""
|
98
|
+
SyntaxNode offset=6, ""
|
99
|
+
SyntaxNode offset=6, ""
|
100
|
+
SyntaxNode offset=6, ""
|
101
|
+
{:contains=>[{:name=>"tomato"}]}
|
102
|
+
|
103
|
+
$ food_ingredient_parser -q -f data/test-cases
|
104
|
+
parsed 35 (100.0%), no result 0 (0.0%)
|
105
|
+
```
|
106
|
+
|
107
|
+
If you want to use the output in (shell)scripts, the options `-e -c` may be quite useful.
|
108
|
+
|
109
|
+
## Test data
|
110
|
+
|
111
|
+
[`data/ingredient-samples-nl`](data/ingredient-samples-nl) contains about 150k
|
112
|
+
real-world ingredient lists found on the Dutch market. Each line contains one ingredient
|
113
|
+
list (newlines are encoded as `\n`, empty lines and those starting with `#` are ignored).
|
114
|
+
Currently almost three quarter is recognized and parsed. We aim to reach at least 90%.
|
115
|
+
|
@@ -0,0 +1,107 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
#
|
3
|
+
# Parser for food ingredient lists.
|
4
|
+
#
|
5
|
+
require 'optparse'
|
6
|
+
|
7
|
+
$:.push(File.expand_path(File.dirname(__FILE__) + "/../lib"))
|
8
|
+
require 'food_ingredient_parser'
|
9
|
+
|
10
|
+
begin
|
11
|
+
require 'pry'
|
12
|
+
def pp(o, color: true)
|
13
|
+
if color
|
14
|
+
Pry::ColorPrinter.pp(o)
|
15
|
+
else
|
16
|
+
puts(o.inspect)
|
17
|
+
end
|
18
|
+
end
|
19
|
+
rescue LoadError
|
20
|
+
# fallback without color printing
|
21
|
+
def pp(o, color: nil)
|
22
|
+
puts(o.inspect)
|
23
|
+
end
|
24
|
+
end
|
25
|
+
|
26
|
+
def colorize(color, s)
|
27
|
+
if color
|
28
|
+
"\e[#{color}m#{s}\e[0;22m"
|
29
|
+
else
|
30
|
+
s
|
31
|
+
end
|
32
|
+
end
|
33
|
+
|
34
|
+
def parse_single(s, parsed=nil, parser: nil, verbosity: 1, print: nil, escape: false, color: false)
|
35
|
+
parser ||= FoodIngredientParser::Parser.new
|
36
|
+
parsed ||= parser.parse(s)
|
37
|
+
|
38
|
+
return unless print.nil? || (parsed && print == :parsed) || (!parsed && print == :noresult)
|
39
|
+
|
40
|
+
puts colorize(color && "0;32", escape ? s.gsub("\n", "\\n") : s) if verbosity > 0
|
41
|
+
|
42
|
+
if parsed
|
43
|
+
puts(parsed.inspect) if verbosity > 1
|
44
|
+
pp(parsed.to_h, color: color) if verbosity > 0
|
45
|
+
else
|
46
|
+
puts "(no result: #{parser.failure_reason})" if verbosity > 0
|
47
|
+
end
|
48
|
+
end
|
49
|
+
|
50
|
+
def parse_file(path, parser: nil, verbosity: 1, print: nil, escape: false, color: false)
|
51
|
+
count_parsed = count_noresult = 0
|
52
|
+
File.foreach(path) do |line|
|
53
|
+
next if line =~ /^#/ # comment
|
54
|
+
next if line =~ /^\s*$/ # empty line
|
55
|
+
|
56
|
+
line = line.gsub('\\n', "\n").strip
|
57
|
+
parsed = parser.parse(line)
|
58
|
+
count_parsed += 1 if parsed
|
59
|
+
count_noresult += 1 unless parsed
|
60
|
+
|
61
|
+
parse_single(line, parsed, parser: parser, verbosity: verbosity, print: print, escape: escape, color: color)
|
62
|
+
end
|
63
|
+
|
64
|
+
pct_parsed = 100.0 * count_parsed / (count_parsed + count_noresult)
|
65
|
+
pct_noresult = 100.0 * count_noresult / (count_parsed + count_noresult)
|
66
|
+
puts "parsed #{colorize(color && "1;32", count_parsed)} (#{pct_parsed.round(1)}%), no result #{colorize(color && "1;31", count_noresult)} (#{pct_noresult.round(1)}%)"
|
67
|
+
end
|
68
|
+
|
69
|
+
verbosity = 1
|
70
|
+
files = []
|
71
|
+
strings = []
|
72
|
+
print = nil
|
73
|
+
escape = false
|
74
|
+
color = true
|
75
|
+
OptionParser.new do |opts|
|
76
|
+
opts.banner = <<-EOF.gsub(/^ /, '')
|
77
|
+
Usage: #{$0} [options] --file|-f <filename>
|
78
|
+
#{$0} [options] --string|-s <ingredients>
|
79
|
+
|
80
|
+
EOF
|
81
|
+
|
82
|
+
opts.on("-f", "--file FILE", "Parse all lines of the file as ingredient lists.") {|f| files << f }
|
83
|
+
opts.on("-s", "--string INGREDIENTS", "Parse specified ingredient list.") {|s| strings << s }
|
84
|
+
|
85
|
+
opts.on("-q", "--[no-]quiet", "Only show summary.") {|q| verbosity = q ? 0 : 1 }
|
86
|
+
opts.on("-p", "--parsed", "Only show lines that were successfully parsed.") {|p| print = :parsed }
|
87
|
+
opts.on("-e", "--escape", "Escape newlines") {|e| escape = true }
|
88
|
+
opts.on("-c", "--[no-]color", "Use color") {|e| color = !!e }
|
89
|
+
opts.on("-n", "--noresult", "Only show lines that had no result.") {|p| print = :noresult }
|
90
|
+
opts.on("-v", "--[no-]verbose", "Show more data (parsed tree).") {|v| verbosity = v ? 2 : 1 }
|
91
|
+
opts.on( "--version", "Show program version.") do
|
92
|
+
puts("food_ingredient_parser v#{FoodIngredientParser::VERSION}")
|
93
|
+
exit
|
94
|
+
end
|
95
|
+
opts.on("-h", "--help", "Show this help") do
|
96
|
+
puts(opts)
|
97
|
+
exit
|
98
|
+
end
|
99
|
+
end.parse!
|
100
|
+
|
101
|
+
if strings.any? || files.any?
|
102
|
+
parser = FoodIngredientParser::Parser.new
|
103
|
+
strings.each {|s| parse_single(s, parser: parser, verbosity: verbosity, print: print, escape: escape, color: color) }
|
104
|
+
files.each {|f| parse_file(f, parser: parser, verbosity: verbosity, print: print, escape: escape, color: color) }
|
105
|
+
else
|
106
|
+
STDERR.puts("Please specify one or more --file or --string arguments (see --help).")
|
107
|
+
end
|
@@ -0,0 +1,29 @@
|
|
1
|
+
$:.unshift(File.expand_path(File.dirname(__FILE__) + '/lib'))
|
2
|
+
require 'food_ingredient_parser/version'
|
3
|
+
|
4
|
+
Gem::Specification.new do |s|
|
5
|
+
s.name = 'food_ingredient_parser'
|
6
|
+
s.version = FoodIngredientParser::VERSION
|
7
|
+
s.date = '2018-08-09'
|
8
|
+
s.summary = 'Parser for ingredient lists found on food products.'
|
9
|
+
s.authors = ['wvengen']
|
10
|
+
s.email = ['dev-ruby@willem.engen.nl']
|
11
|
+
s.homepage = 'https://github.com/q-m/food-ingredient-parser-ruby'
|
12
|
+
s.license = 'MIT'
|
13
|
+
s.description = <<-EOD
|
14
|
+
Food products often contain an ingredient list of some sort. This parser
|
15
|
+
tries to recognize the syntax and returns a structured representation of the
|
16
|
+
food ingredients.
|
17
|
+
EOD
|
18
|
+
s.metadata = {
|
19
|
+
'bug_tracker_uri' => 'https://github.com/q-m/food-ingredient-parser-ruby/issues',
|
20
|
+
'source_code_uri' => 'https://github.com/q-m/food-ingredient-parser-ruby',
|
21
|
+
}
|
22
|
+
|
23
|
+
s.files = `git ls-files *.gemspec lib`.split("\n")
|
24
|
+
s.executables = `git ls-files bin`.split("\n").map(&File.method(:basename))
|
25
|
+
s.extra_rdoc_files = ['README.md', 'LICENSE']
|
26
|
+
s.require_paths = ['lib']
|
27
|
+
|
28
|
+
s.add_runtime_dependency 'treetop', '~> 1.6'
|
29
|
+
end
|
@@ -0,0 +1,30 @@
|
|
1
|
+
module FoodIngredientParser::Grammar
|
2
|
+
grammar Amount
|
3
|
+
include Common
|
4
|
+
|
5
|
+
rule amount
|
6
|
+
'(' ws* amount:simple_amount ws* ')' <AmountNode> /
|
7
|
+
'[' ws* amount:simple_amount ws* ']' <AmountNode> /
|
8
|
+
'{' ws* amount:simple_amount ws* '}' <AmountNode> /
|
9
|
+
amount:simple_amount <AmountNode>
|
10
|
+
end
|
11
|
+
|
12
|
+
rule simple_amount
|
13
|
+
( (
|
14
|
+
'of which' / 'at least' /
|
15
|
+
'waarvan' / 'ten minste' / 'tenminste' / 'minimaal'
|
16
|
+
) ws* )?
|
17
|
+
[<>]? ws*
|
18
|
+
simple_amount_quantity
|
19
|
+
( ws+ (
|
20
|
+
'minimum' /
|
21
|
+
'minimaal' / 'minimum'
|
22
|
+
) )?
|
23
|
+
end
|
24
|
+
|
25
|
+
rule simple_amount_quantity
|
26
|
+
number ( ws* '-' ws* number )? ws* ( '%' / 'g' / 'mg' / 'gram' / 'ml' )
|
27
|
+
end
|
28
|
+
|
29
|
+
end
|
30
|
+
end
|
@@ -0,0 +1,150 @@
|
|
1
|
+
module FoodIngredientParser::Grammar
|
2
|
+
grammar Common
|
3
|
+
|
4
|
+
rule ws
|
5
|
+
" " / "\t"
|
6
|
+
end
|
7
|
+
|
8
|
+
rule newline
|
9
|
+
"\n"
|
10
|
+
end
|
11
|
+
|
12
|
+
rule char
|
13
|
+
[[:alnum:]] /
|
14
|
+
fraction /
|
15
|
+
[-/\'’+=_{}&] /
|
16
|
+
[®] /
|
17
|
+
[¿?] / # weird characters turning up in names (e.g. encoding issues)
|
18
|
+
[₁₂₃₄₅₆₇₈₉] # can occur with vitamins
|
19
|
+
#[A-Za-z0-9] / [-\'+/=?;!*#@$_%] / [#xC0-#xD6] / [#xD8-#xF6] / [#xF8-#x2FF] / [#x370-#x37D] / [#x37F-#x1FFF] / [#x200C-#x200D] / [#x2070-#x218F] / [#x2C00-#x2FEF] / [#x3001-#xD7FF] / [#xF900-#xFDCF] / [#xFDF0-#xFFFD] / [#x10000-#xEFFFF]
|
20
|
+
end
|
21
|
+
|
22
|
+
rule mark
|
23
|
+
# mark referencing a footnote
|
24
|
+
[¹²³⁴⁵ᵃᵇᶜᵈᵉᶠᵍªº] '⁾'? / '⁽' [¹²³⁴⁵ᵃᵇᶜᵈᵉᶠᵍªº] '⁾' / [†‡•°#^] / '*'+
|
25
|
+
end
|
26
|
+
|
27
|
+
rule digit
|
28
|
+
[0-9]
|
29
|
+
end
|
30
|
+
|
31
|
+
rule fraction
|
32
|
+
[½⅓⅔¼¾⅕⅖⅗⅘⅙⅚⅐⅛⅜⅝⅞⅑⅒]
|
33
|
+
end
|
34
|
+
|
35
|
+
rule number
|
36
|
+
digit+ [,.] digit+ / digit+ ws* fraction / fraction / digit+
|
37
|
+
end
|
38
|
+
|
39
|
+
rule word
|
40
|
+
abbrev / char+
|
41
|
+
end
|
42
|
+
|
43
|
+
rule word_nas
|
44
|
+
# word, but don't include the trailing '-' that may occure before an 'and'
|
45
|
+
abbrev / ( !andsep char )+
|
46
|
+
end
|
47
|
+
|
48
|
+
rule and
|
49
|
+
( 'and' / 'en' / 'und' / '&' ) !char
|
50
|
+
end
|
51
|
+
|
52
|
+
# we want to match "a and b" but not "a- and bthing", this allows to avoid the latter
|
53
|
+
rule andsep
|
54
|
+
'-' ws+ and
|
55
|
+
end
|
56
|
+
|
57
|
+
rule abbrev
|
58
|
+
# These are listed explicitely to avoid incorrect interpretations, and allow missing trailing dots.
|
59
|
+
# To get an idea of what occurs (second one omits trailing dots):
|
60
|
+
# cat data/ingredient-samples-nl | perl -ne '$_=lc($_); /\b(([a-z]\.)+[a-z]\.?)\W/ && print "$1\n"' | sort | uniq -c | sort -rn
|
61
|
+
# cat data/ingredient-samples-nl | perl -ne '$_=lc($_); /\b(([a-z]\.)+[a-z])\W/ && print "$1\n"' | sort | uniq -c | sort -rn
|
62
|
+
# Finally, you can generate the full list using this command:
|
63
|
+
# cat data/ingredient-samples-nl | perl -ne '$_=lc($_); /\b(([a-z]\.)+[a-z])\W/ && print "$1\n"' | sort | uniq | sed "s/^/'/;s/$/'i \//"
|
64
|
+
(
|
65
|
+
'a.o.p'i /
|
66
|
+
'b.g.a'i /
|
67
|
+
'b.o.b'i /
|
68
|
+
'c.a'i /
|
69
|
+
'c.i'i /
|
70
|
+
'd.e'i /
|
71
|
+
'd.m.v'i /
|
72
|
+
'd.o.c'i /
|
73
|
+
'd.o.p'i /
|
74
|
+
'd.s'i /
|
75
|
+
'e.a'i /
|
76
|
+
'e.g'i /
|
77
|
+
'e.u'i /
|
78
|
+
'f.i.l'i /
|
79
|
+
'f.o.s'i /
|
80
|
+
'i.a'i /
|
81
|
+
'i.d'i /
|
82
|
+
'i.e'i /
|
83
|
+
'i.g.m.e'i /
|
84
|
+
'i.g.p'i /
|
85
|
+
'i.m.v'i /
|
86
|
+
'i.o'i /
|
87
|
+
'i.v.m'i /
|
88
|
+
'l.s.l'i /
|
89
|
+
'n.a'i /
|
90
|
+
'n.b'i /
|
91
|
+
'n.o'i /
|
92
|
+
'n.v.t'i /
|
93
|
+
'o.a'i /
|
94
|
+
'o.b.v'i /
|
95
|
+
'p.d.o'i /
|
96
|
+
'p.g.i'i /
|
97
|
+
'q.s'i /
|
98
|
+
's.l'i /
|
99
|
+
's.s'i /
|
100
|
+
't.o.v'i /
|
101
|
+
'u.h.t'i /
|
102
|
+
'v.g'i /
|
103
|
+
'v.s'i /
|
104
|
+
'w.a'i /
|
105
|
+
'w.o'i /
|
106
|
+
'w.v'i /
|
107
|
+
# special words and abbreviations (not auto-generated)
|
108
|
+
'vit.'i /
|
109
|
+
'denat.'i /
|
110
|
+
'N°'i /
|
111
|
+
'°C'i /
|
112
|
+
# word combinations that should not be split (not auto-generated)
|
113
|
+
# @todo this really would benefit from matching known ingredients instead of hardcoding
|
114
|
+
( 'oliën'i / 'olien'i / 'olië'i / 'olie'i ) ws+ and ws+ ( 'vetten'i / 'vet'i ) /
|
115
|
+
'palm'i ws+ and ws+ 'kokosvet'i /
|
116
|
+
color ( ws+ and ws+ color )+ /
|
117
|
+
color2 ( ws+ and ws+ color2 )+ /
|
118
|
+
'kruiden'i ws+ and ws+ 'specerijen'i /
|
119
|
+
'kruiden'i ws+ and ws+ 'specerij'i /
|
120
|
+
'specerijen'i ws+ and ws+ 'kruiden'i /
|
121
|
+
'vitamine'i 'n'i? ws+ and ws+ 'mineralen'i /
|
122
|
+
'lactose'i ws+ and ws+ 'melk'i ( 'eiwit'i 'en'i? )? /
|
123
|
+
'granen'i ws+ and ws+ 'zaden'i /
|
124
|
+
'gekookt'i [eE]? ws+ and ws+ 'gemarineerd'i [eE]? /
|
125
|
+
'mono'i ws+ and ws+ 'diglyceriden'i /
|
126
|
+
'guarpitmeel'i ws+ and ws+ 'natriumalginaat'i /
|
127
|
+
'vlees'i ws+ and ws+ 'dierlijke bijproducten'i /
|
128
|
+
'vis'i ws+ and ws+ 'visbijproducten'i /
|
129
|
+
'glucose'i ws+ and ws+ 'fructosestroop'i /
|
130
|
+
'ijzeroxiden'i ws+ and ws+ 'hydroxiden'i /
|
131
|
+
char+ 'sap'i ws+ and ws+ 'overige vruchtensappen'i /
|
132
|
+
char* 'sap'i ( ws+ 'uit concentraat'i / ws+ 'uit sapconcentraat'i )? ws+ and ws+ 'vruchten'i? 'puree'i /
|
133
|
+
( 'vit.'i / 'vitamine'i / 'vitamin' ) ws+ [a-zA-Z] [0-9]* ws+ and ws+ [a-zA-Z] [0-9]*
|
134
|
+
)
|
135
|
+
'.'? ![[:alpha:]]
|
136
|
+
end
|
137
|
+
|
138
|
+
rule color
|
139
|
+
# used for paprika, honey ("yellow and white honey") (nouns)
|
140
|
+
'red'i / 'green'i / 'yellow'i / 'white'i / 'black'i /
|
141
|
+
'rood'i / 'groen'i / 'geel'i / 'wit'i / 'zwart'i
|
142
|
+
end
|
143
|
+
|
144
|
+
rule color2
|
145
|
+
# adjective colors (can not occur together with noun colors in a list)
|
146
|
+
'rode'i / 'groene'i / 'gele'i / 'witte'i / 'zwarte'i
|
147
|
+
end
|
148
|
+
|
149
|
+
end
|
150
|
+
end
|
@@ -0,0 +1,12 @@
|
|
1
|
+
module FoodIngredientParser::Grammar
|
2
|
+
grammar Ingredient
|
3
|
+
include IngredientSimple
|
4
|
+
include IngredientNested
|
5
|
+
include IngredientColoned
|
6
|
+
|
7
|
+
rule ingredient
|
8
|
+
ws* ( ingredient_nested / ingredient_coloned / ingredient_simple_with_amount )
|
9
|
+
end
|
10
|
+
|
11
|
+
end
|
12
|
+
end
|
@@ -0,0 +1,41 @@
|
|
1
|
+
module FoodIngredientParser::Grammar
|
2
|
+
grammar IngredientColoned
|
3
|
+
include Common
|
4
|
+
include Amount
|
5
|
+
include IngredientSimple
|
6
|
+
|
7
|
+
rule ingredient_coloned
|
8
|
+
ing:ingredient_simple ws* ':' ws* amount:amount post:( ws* '}' )? !( ws* word ) <IngredientNode> /
|
9
|
+
ing:ingredient_simple ws* ':' post:( ws* '}' )? ws* contains:( ingredient_coloned_inner_list ) <NestedIngredientNode>
|
10
|
+
end
|
11
|
+
|
12
|
+
rule ingredient_coloned_inner_list
|
13
|
+
contains:( ingredient_coloned_simple_with_amount_and_nest ( ws+ and ws+ ingredient_coloned_simple_with_amount_and_nest )+ ) <ListNode> /
|
14
|
+
contains:( ingredient_coloned_simple_with_amount_and_nest ws* ( '/'+ ws* ingredient_coloned_simple_with_amount_and_nest )* ) <ListNode>
|
15
|
+
end
|
16
|
+
|
17
|
+
# @see IngredientSimple#ingredient_simple
|
18
|
+
rule ingredient_coloned_simple
|
19
|
+
name:( ingredient_coloned_word_nas ( andsep? ws+ !amount !and ingredient_coloned_word_nas )* ) ws? mark:mark <IngredientNode> /
|
20
|
+
name:( ingredient_coloned_word_nas ( andsep? ws+ !amount !and ingredient_coloned_word_nas )* ) <IngredientNode>
|
21
|
+
end
|
22
|
+
|
23
|
+
# @see IngredientSimple#ingredient_simple_with_amount
|
24
|
+
rule ingredient_coloned_simple_with_amount
|
25
|
+
pre:( '{' ws* )? amount:amount ws+ ing:ingredient_coloned_simple <IngredientNode> /
|
26
|
+
ing:ingredient_coloned_simple ws* amount:amount post:( ws* '}' )? (ws? mark:mark)? <IngredientNode> /
|
27
|
+
ing:ingredient_coloned_simple <IngredientNode>
|
28
|
+
end
|
29
|
+
|
30
|
+
rule ingredient_coloned_simple_with_amount_and_nest
|
31
|
+
ing:ingredient_coloned_simple_with_amount ws* '(' ws* contains:ingredient_coloned_simple_with_amount ws* ')' ( ws* '}' )? <NestedIngredientNode> /
|
32
|
+
ingredient_coloned_simple_with_amount
|
33
|
+
end
|
34
|
+
|
35
|
+
# @see Common#word
|
36
|
+
rule ingredient_coloned_word_nas
|
37
|
+
abbrev / ( !'/' !andsep char )+
|
38
|
+
end
|
39
|
+
|
40
|
+
end
|
41
|
+
end
|
@@ -0,0 +1,28 @@
|
|
1
|
+
module FoodIngredientParser::Grammar
|
2
|
+
grammar IngredientNested
|
3
|
+
include Common
|
4
|
+
include Amount
|
5
|
+
include IngredientSimple
|
6
|
+
|
7
|
+
rule ingredient_nested
|
8
|
+
( ing:ingredient_simple ws* '(' contains:ingredient_nested_in ws* ')' ws? mark:mark ws* amount:amount <NestedIngredientNode> ) /
|
9
|
+
( ing:ingredient_simple ws* '(' contains:ingredient_nested_in ws* ')' ws* amount:amount <NestedIngredientNode> ) /
|
10
|
+
( ing:ingredient_simple_with_amount ws* '(' contains:ingredient_nested_in ws* ')' ws? mark:mark <NestedIngredientNode> ) /
|
11
|
+
( ing:ingredient_simple_with_amount ws* '(' contains:ingredient_nested_in ws* ')' <NestedIngredientNode> ) /
|
12
|
+
( ing:ingredient_simple ws* '[' contains:ingredient_nested_in ws* ']' ws? mark:mark ws* amount:amount <NestedIngredientNode> ) /
|
13
|
+
( ing:ingredient_simple ws* '[' contains:ingredient_nested_in ws* ']' ws* amount:amount <NestedIngredientNode> ) /
|
14
|
+
( ing:ingredient_simple_with_amount ws* '[' contains:ingredient_nested_in ws* ']' ws? mark:mark <NestedIngredientNode> ) /
|
15
|
+
( ing:ingredient_simple_with_amount ws* '[' contains:ingredient_nested_in ws* ']' <NestedIngredientNode> )
|
16
|
+
end
|
17
|
+
|
18
|
+
rule ingredient_nested_in
|
19
|
+
( ingredient_nested_contains (ws* ':')? ws+ )? ws* contains:list ws* '.'?
|
20
|
+
end
|
21
|
+
|
22
|
+
rule ingredient_nested_contains
|
23
|
+
'contains'i /
|
24
|
+
'bevat'i
|
25
|
+
end
|
26
|
+
|
27
|
+
end
|
28
|
+
end
|
@@ -0,0 +1,21 @@
|
|
1
|
+
module FoodIngredientParser::Grammar
|
2
|
+
grammar IngredientSimple
|
3
|
+
include Common
|
4
|
+
include Amount
|
5
|
+
|
6
|
+
rule ingredient_simple
|
7
|
+
name:( word_nas ( andsep? ws+ !amount !and word_nas )* ) ws? mark:mark <IngredientNode> /
|
8
|
+
name:( word_nas ( andsep? ws+ !amount !and word_nas )* ) <IngredientNode> /
|
9
|
+
# We've tried to omit 'and' from the ingredient, but if it doesn't work out, do it anyway.
|
10
|
+
name:( word_nas ( andsep? ws+ !amount word_nas )* ) ws? mark:mark <IngredientNode> /
|
11
|
+
name:( word_nas ( andsep? ws+ !amount word_nas )* ) <IngredientNode>
|
12
|
+
end
|
13
|
+
|
14
|
+
rule ingredient_simple_with_amount
|
15
|
+
pre:( '{' ws* )? amount:amount ws+ ing:ingredient_simple <IngredientNode> /
|
16
|
+
ing:ingredient_simple ws* amount:amount post:( ws* '}' )? (ws? mark:mark)? <IngredientNode> /
|
17
|
+
ing:ingredient_simple <IngredientNode>
|
18
|
+
end
|
19
|
+
|
20
|
+
end
|
21
|
+
end
|
@@ -0,0 +1,14 @@
|
|
1
|
+
module FoodIngredientParser::Grammar
|
2
|
+
grammar List
|
3
|
+
include Common
|
4
|
+
include Ingredient
|
5
|
+
|
6
|
+
rule list
|
7
|
+
contains:(ingredient ( ws* '|' ws* ingredient )+ ( ws+ and ws+ ingredient )? ) <ListNode> /
|
8
|
+
contains:(ingredient ( ws* ';' ws* ingredient )+ ( ws+ and ws+ ingredient )? ) <ListNode> /
|
9
|
+
contains:(ingredient ( ws* ',' ws* ingredient )+ ( ws+ and ws+ ingredient )? ) <ListNode> /
|
10
|
+
contains:(ingredient ( ws* '.' ws* ingredient )+ ( ws+ and ws+ ingredient )? ) <ListNode> /
|
11
|
+
contains:(ingredient ( ws+ and ws+ ingredient )? ) <ListNode>
|
12
|
+
end
|
13
|
+
end
|
14
|
+
end
|
@@ -0,0 +1,23 @@
|
|
1
|
+
module FoodIngredientParser::Grammar
|
2
|
+
grammar ListColoned
|
3
|
+
include Common
|
4
|
+
include IngredientSimple
|
5
|
+
include Ingredient
|
6
|
+
|
7
|
+
rule list_coloned
|
8
|
+
contains:( ( list_coloned_ingredient ws* '.' ws* )+ list_coloned_ingredient? ) <ListNode> /
|
9
|
+
contains:( ( list_coloned_ingredient ws* ';' ws* )+ list_coloned_ingredient? ) <ListNode> /
|
10
|
+
contains:( list_coloned_ingredient ) <ListNode>
|
11
|
+
end
|
12
|
+
|
13
|
+
rule list_coloned_inner_list
|
14
|
+
contains:( ingredient ( ws* ',' ws* ingredient )* ) <ListNode>
|
15
|
+
end
|
16
|
+
|
17
|
+
rule list_coloned_ingredient
|
18
|
+
ing:ingredient_simple_with_amount ws* ':' ws* amount:amount post:( ws* '}' )? <IngredientNode> /
|
19
|
+
ing:ingredient_simple_with_amount ws* ':' post:( ws* '}' )? ws* contains:list_coloned_inner_list <NestedIngredientNode>
|
20
|
+
end
|
21
|
+
|
22
|
+
end
|
23
|
+
end
|
@@ -0,0 +1,16 @@
|
|
1
|
+
module FoodIngredientParser::Grammar
|
2
|
+
grammar ListNewlined
|
3
|
+
include Common
|
4
|
+
include IngredientSimple
|
5
|
+
include List
|
6
|
+
|
7
|
+
rule list_newlined
|
8
|
+
contains:( ( list_newlined_ingredient_nested ws* newline newline )* list_newlined_ingredient_nested ) <ListNode>
|
9
|
+
end
|
10
|
+
|
11
|
+
rule list_newlined_ingredient_nested
|
12
|
+
ws* ing:ingredient_simple ws* ':'? ws* newline contains:list ( ws* '.' )? <NestedIngredientNode>
|
13
|
+
end
|
14
|
+
|
15
|
+
end
|
16
|
+
end
|
@@ -0,0 +1,51 @@
|
|
1
|
+
module FoodIngredientParser::Grammar
|
2
|
+
grammar Root
|
3
|
+
include Common
|
4
|
+
include List
|
5
|
+
include ListColoned
|
6
|
+
include ListNewlined
|
7
|
+
|
8
|
+
rule root
|
9
|
+
'"'?
|
10
|
+
root_prefix? ws*
|
11
|
+
contains:( list_newlined / list_coloned / list )
|
12
|
+
notes:(
|
13
|
+
root_mark_sentences_in_list? ws*
|
14
|
+
( ( '.' ws* newline* / '.'? ws* newline+ ) ws* root_sentences? ws* )?
|
15
|
+
)
|
16
|
+
'"'?
|
17
|
+
<RootNode>
|
18
|
+
end
|
19
|
+
|
20
|
+
rule root_prefix
|
21
|
+
(
|
22
|
+
'ingredients'i / 'contains'i /
|
23
|
+
('ingred'i [IÏiï] [EËeë] 'n'i ( 't'i 'en'i? 'declaratie'i? )? ) / 'bevat'i / 'dit zit er in'i / 'samenstelling'i /
|
24
|
+
'zutaten'i
|
25
|
+
)
|
26
|
+
( ws* [:;.] ( ws* newline )? / ws* newline / ws ) ws* # optional colon or other separator
|
27
|
+
"'"? ws* # stray quote occurs sometimes
|
28
|
+
end
|
29
|
+
|
30
|
+
rule root_sentences
|
31
|
+
( root_sentence ws* )+ root_sentence_open? / root_sentence_open
|
32
|
+
end
|
33
|
+
|
34
|
+
rule root_sentence
|
35
|
+
root_sentence_open ( '.' / ';' / newline+ )
|
36
|
+
end
|
37
|
+
|
38
|
+
rule root_sentence_open
|
39
|
+
( word / ws / [,:()%] / '[' / ']' / mark )+ <NoteNode>
|
40
|
+
end
|
41
|
+
|
42
|
+
rule root_mark_sentences_in_list
|
43
|
+
( ( ws* [,.] / ws ) ws* root_mark_sentence_in_list )+
|
44
|
+
end
|
45
|
+
|
46
|
+
rule root_mark_sentence_in_list
|
47
|
+
mark ws* root_sentence_open <NoteNode>
|
48
|
+
end
|
49
|
+
|
50
|
+
end
|
51
|
+
end
|
@@ -0,0 +1,16 @@
|
|
1
|
+
require 'treetop'
|
2
|
+
require_relative 'nodes'
|
3
|
+
|
4
|
+
# @todo find a way to auto-generate Ruby from Treetop files when building gem,
|
5
|
+
# see https://stackoverflow.com/q/37794587/2866660
|
6
|
+
|
7
|
+
Treetop.load File.dirname(__FILE__) + '/grammar/common'
|
8
|
+
Treetop.load File.dirname(__FILE__) + '/grammar/amount'
|
9
|
+
Treetop.load File.dirname(__FILE__) + '/grammar/ingredient_simple'
|
10
|
+
Treetop.load File.dirname(__FILE__) + '/grammar/ingredient_nested'
|
11
|
+
Treetop.load File.dirname(__FILE__) + '/grammar/ingredient_coloned'
|
12
|
+
Treetop.load File.dirname(__FILE__) + '/grammar/ingredient'
|
13
|
+
Treetop.load File.dirname(__FILE__) + '/grammar/list'
|
14
|
+
Treetop.load File.dirname(__FILE__) + '/grammar/list_coloned'
|
15
|
+
Treetop.load File.dirname(__FILE__) + '/grammar/list_newlined'
|
16
|
+
Treetop.load File.dirname(__FILE__) + '/grammar/root'
|
@@ -0,0 +1,69 @@
|
|
1
|
+
require 'treetop/runtime'
|
2
|
+
|
3
|
+
# Needs to be in grammar namespace so Treetop can find the nodes.
|
4
|
+
module FoodIngredientParser::Grammar
|
5
|
+
|
6
|
+
# Treetop syntax node with our additions, use this as parent for all our own nodes.
|
7
|
+
class SyntaxNode < Treetop::Runtime::SyntaxNode
|
8
|
+
private
|
9
|
+
|
10
|
+
def to_a_deep(n, cls)
|
11
|
+
if n.is_a?(cls)
|
12
|
+
[n]
|
13
|
+
elsif n.nonterminal?
|
14
|
+
n.elements.map {|m| to_a_deep(m, cls) }.flatten(1).compact
|
15
|
+
end
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
# Root object, contains everything else.
|
20
|
+
class RootNode < SyntaxNode
|
21
|
+
def to_h
|
22
|
+
h = { contains: contains.to_a }
|
23
|
+
if notes && notes_ary = to_a_deep(notes, NoteNode)&.map(&:text_value)
|
24
|
+
h[:notes] = notes_ary if notes_ary.length > 0
|
25
|
+
end
|
26
|
+
h
|
27
|
+
end
|
28
|
+
end
|
29
|
+
|
30
|
+
# List of ingredients.
|
31
|
+
class ListNode < SyntaxNode
|
32
|
+
def to_a
|
33
|
+
to_a_deep(contains, IngredientNode).map(&:to_h)
|
34
|
+
end
|
35
|
+
end
|
36
|
+
|
37
|
+
# Ingredient
|
38
|
+
class IngredientNode < SyntaxNode
|
39
|
+
def to_h
|
40
|
+
h = {}
|
41
|
+
h.merge!(to_a_deep(ing, IngredientNode)&.first&.to_h || {}) if respond_to?(:ing)
|
42
|
+
h.merge!(to_a_deep(amount, AmountNode)&.first&.to_h || {}) if respond_to?(:amount)
|
43
|
+
h[:name] = name.text_value if respond_to?(:name)
|
44
|
+
h[:name] = pre.text_value + h[:name] if respond_to?(:pre)
|
45
|
+
h[:name] = h[:name] + post.text_value if respond_to?(:post)
|
46
|
+
h[:mark] = mark.text_value if respond_to?(:mark) && mark.text_value != ''
|
47
|
+
h
|
48
|
+
end
|
49
|
+
end
|
50
|
+
|
51
|
+
# Ingredient with containing ingredients.
|
52
|
+
class NestedIngredientNode < IngredientNode
|
53
|
+
def to_h
|
54
|
+
super.merge({ contains: to_a_deep(contains, IngredientNode).map(&:to_h) })
|
55
|
+
end
|
56
|
+
end
|
57
|
+
|
58
|
+
# Amount, specifying an ingredient.
|
59
|
+
class AmountNode < SyntaxNode
|
60
|
+
def to_h
|
61
|
+
{ amount: amount.text_value }
|
62
|
+
end
|
63
|
+
end
|
64
|
+
|
65
|
+
# Note at the end of the ingredient list.
|
66
|
+
class NoteNode < SyntaxNode
|
67
|
+
end
|
68
|
+
|
69
|
+
end
|
@@ -0,0 +1,34 @@
|
|
1
|
+
require_relative 'grammar'
|
2
|
+
|
3
|
+
module FoodIngredientParser
|
4
|
+
class Parser
|
5
|
+
|
6
|
+
# Create a new food ingredient parser
|
7
|
+
# @return [FoodIngredientParser]
|
8
|
+
def initialize
|
9
|
+
@parser = Grammar::RootParser.new
|
10
|
+
end
|
11
|
+
|
12
|
+
# Parse food ingredient list text into a structured representation.
|
13
|
+
# @option clean [Boolean] pass +false+ to disable correcting frequently occuring issues
|
14
|
+
# @return [Hash] structured representation of food ingredients
|
15
|
+
def parse(s, clean: true)
|
16
|
+
s = clean(s) if clean
|
17
|
+
@parser.parse(s)
|
18
|
+
end
|
19
|
+
|
20
|
+
private
|
21
|
+
|
22
|
+
def clean(s)
|
23
|
+
s.gsub!("\u00ad", "") # strip soft hyphen
|
24
|
+
s.gsub!("\u0092", "'") # windows-1252 apostrophe - https://stackoverflow.com/a/15564279/2866660
|
25
|
+
s.gsub!("aÄs", "aïs") # encoding issue for maïs
|
26
|
+
s.gsub!("ï", "ï") # encoding issue
|
27
|
+
s.gsub!("ë", "ë") # encoding issue
|
28
|
+
s.gsub!(/\A\s*"(.*)"\s*\z/, '\1') # enclosing double quotation marks
|
29
|
+
s.gsub!(/\A\s*'(.*)'\s*\z/, '\1') # enclosing single quotation marks
|
30
|
+
s
|
31
|
+
end
|
32
|
+
|
33
|
+
end
|
34
|
+
end
|
metadata
ADDED
@@ -0,0 +1,85 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: food_ingredient_parser
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 1.0.0.pre.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- wvengen
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2018-08-09 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: treetop
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.6'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.6'
|
27
|
+
description: |2
|
28
|
+
Food products often contain an ingredient list of some sort. This parser
|
29
|
+
tries to recognize the syntax and returns a structured representation of the
|
30
|
+
food ingredients.
|
31
|
+
email:
|
32
|
+
- dev-ruby@willem.engen.nl
|
33
|
+
executables:
|
34
|
+
- food_ingredient_parser
|
35
|
+
extensions: []
|
36
|
+
extra_rdoc_files:
|
37
|
+
- README.md
|
38
|
+
- LICENSE
|
39
|
+
files:
|
40
|
+
- LICENSE
|
41
|
+
- README.md
|
42
|
+
- bin/food_ingredient_parser
|
43
|
+
- food_ingredient_parser.gemspec
|
44
|
+
- lib/food_ingredient_parser.rb
|
45
|
+
- lib/food_ingredient_parser/grammar.rb
|
46
|
+
- lib/food_ingredient_parser/grammar/amount.treetop
|
47
|
+
- lib/food_ingredient_parser/grammar/common.treetop
|
48
|
+
- lib/food_ingredient_parser/grammar/ingredient.treetop
|
49
|
+
- lib/food_ingredient_parser/grammar/ingredient_coloned.treetop
|
50
|
+
- lib/food_ingredient_parser/grammar/ingredient_nested.treetop
|
51
|
+
- lib/food_ingredient_parser/grammar/ingredient_simple.treetop
|
52
|
+
- lib/food_ingredient_parser/grammar/list.treetop
|
53
|
+
- lib/food_ingredient_parser/grammar/list_coloned.treetop
|
54
|
+
- lib/food_ingredient_parser/grammar/list_newlined.treetop
|
55
|
+
- lib/food_ingredient_parser/grammar/root.treetop
|
56
|
+
- lib/food_ingredient_parser/nodes.rb
|
57
|
+
- lib/food_ingredient_parser/parser.rb
|
58
|
+
- lib/food_ingredient_parser/version.rb
|
59
|
+
homepage: https://github.com/q-m/food-ingredient-parser-ruby
|
60
|
+
licenses:
|
61
|
+
- MIT
|
62
|
+
metadata:
|
63
|
+
bug_tracker_uri: https://github.com/q-m/food-ingredient-parser-ruby/issues
|
64
|
+
source_code_uri: https://github.com/q-m/food-ingredient-parser-ruby
|
65
|
+
post_install_message:
|
66
|
+
rdoc_options: []
|
67
|
+
require_paths:
|
68
|
+
- lib
|
69
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
70
|
+
requirements:
|
71
|
+
- - ">="
|
72
|
+
- !ruby/object:Gem::Version
|
73
|
+
version: '0'
|
74
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
75
|
+
requirements:
|
76
|
+
- - ">"
|
77
|
+
- !ruby/object:Gem::Version
|
78
|
+
version: 1.3.1
|
79
|
+
requirements: []
|
80
|
+
rubyforge_project:
|
81
|
+
rubygems_version: 2.6.13
|
82
|
+
signing_key:
|
83
|
+
specification_version: 4
|
84
|
+
summary: Parser for ingredient lists found on food products.
|
85
|
+
test_files: []
|