termextractor 0.0.16
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/lib/extract_set_terms.rb +92 -0
- data/lib/term_extractor.rb +46 -0
- metadata +45 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: b96a8a2568c9b0f2bb0b17b07a6d0131b39ed0e5
|
4
|
+
data.tar.gz: 2f1612dfd0564eda138957fd50d0a6b058483b15
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 2b70ffec27aa30dc168f674175693bd1dd31f0ed044af7c10ea2a39591285a373768e8b8e85828e8e07f5ec38a2316763885178368f86b1acf1f3fa134610f9e
|
7
|
+
data.tar.gz: 0c0bb009fa834204d765965aca672b2f07cbef92f8821d3edae4aa1b58df73c7dd0f2bffb0fabe058794b58cf0afbb25175df46494a5880e88150298a5f9daf0
|
@@ -0,0 +1,92 @@
|
|
1
|
+
class ExtractSetTerms
|
2
|
+
def initialize(item, extract_field, to_extract, extract_term_fields, case_sensitive, save_field)
|
3
|
+
@item = item
|
4
|
+
@extract_field = extract_field
|
5
|
+
|
6
|
+
@to_extract = JSON.parse(to_extract)
|
7
|
+
@extract_term_fields = extract_term_fields
|
8
|
+
@case_sensitive = case_sensitive
|
9
|
+
|
10
|
+
@extract_dict = Hash.new
|
11
|
+
@save_field = save_field
|
12
|
+
@item_out = item
|
13
|
+
end
|
14
|
+
|
15
|
+
# Gets a list of terms to extract
|
16
|
+
def processHashInput
|
17
|
+
# Go through each item then each field
|
18
|
+
@to_extract.each do |ex_key, ex_value|
|
19
|
+
ex_value.each do |ex_field, ex_term|
|
20
|
+
|
21
|
+
# Check if it is the right field
|
22
|
+
if ex_field == @extract_term_fields || @extract_term_fields.include?(ex_field)
|
23
|
+
# Make dictionary of terms to extract and overall mapping
|
24
|
+
ex_term.is_a?(Array) ? processArrayInput(ex_term, ex_key) : @extract_dict[term] = ex_key
|
25
|
+
end
|
26
|
+
|
27
|
+
end
|
28
|
+
end
|
29
|
+
end
|
30
|
+
|
31
|
+
# Add all items in array to dictionary of terms to extract
|
32
|
+
def processArrayInput(extract_arr, map_val)
|
33
|
+
extract_arr.each do |term|
|
34
|
+
map_val = term if map_val == nil
|
35
|
+
@extract_dict[term] = map_val
|
36
|
+
end
|
37
|
+
end
|
38
|
+
|
39
|
+
# Check if the term appears in the text
|
40
|
+
def matchTerm?(term, text, case_sensitive)
|
41
|
+
# Downcase term and text if not case sensitive
|
42
|
+
if case_sensitive == false
|
43
|
+
term = term.downcase
|
44
|
+
text = text.downcase
|
45
|
+
end
|
46
|
+
|
47
|
+
# Return if it maches
|
48
|
+
if text.to_s.match(/\b(#{term})\b/)
|
49
|
+
return true
|
50
|
+
end
|
51
|
+
end
|
52
|
+
|
53
|
+
# Check if item is case sensitive
|
54
|
+
def isCaseSensitive?(term)
|
55
|
+
if @case_sensitive == "case-sensitive"
|
56
|
+
return true
|
57
|
+
elsif @case_sensitive == "case-insensitive"
|
58
|
+
return false
|
59
|
+
else
|
60
|
+
# Handle item by item variations
|
61
|
+
is_case_sensitive = @to_extract[term[1]][@case_sensitive]
|
62
|
+
if is_case_sensitive == "Yes"
|
63
|
+
return true
|
64
|
+
else return false
|
65
|
+
end
|
66
|
+
end
|
67
|
+
end
|
68
|
+
|
69
|
+
# Process input list and go through all terms and fields
|
70
|
+
def extractTerms
|
71
|
+
# Process input list
|
72
|
+
@to_extract.is_a?(Hash) ? processHashInput : processArrayInput(@to_extract, nil)
|
73
|
+
@item_out[@save_field] = Array.new
|
74
|
+
|
75
|
+
# Go through each term and field to check for matches
|
76
|
+
@extract_dict.each do |term|
|
77
|
+
item_case_sensitivity = isCaseSensitive?(term)
|
78
|
+
@extract_field.each do |field|
|
79
|
+
|
80
|
+
# Add to list of terms if it matches
|
81
|
+
if matchTerm?(term[0], @item[field], item_case_sensitivity)
|
82
|
+
@item_out[@save_field].push(term[1])
|
83
|
+
end
|
84
|
+
|
85
|
+
end
|
86
|
+
end
|
87
|
+
|
88
|
+
# Deduplicate and return
|
89
|
+
@item_out[@save_field].uniq!
|
90
|
+
return @item_out
|
91
|
+
end
|
92
|
+
end
|
@@ -0,0 +1,46 @@
|
|
1
|
+
require 'json'
|
2
|
+
load 'extract_set_terms.rb'
|
3
|
+
|
4
|
+
class TermExtractor
|
5
|
+
def initialize(input, extract_from, save_field)
|
6
|
+
@input = JSON.parse(input)
|
7
|
+
@extract_from = extract_from
|
8
|
+
@save_field = save_field
|
9
|
+
|
10
|
+
@output = Array.new
|
11
|
+
end
|
12
|
+
|
13
|
+
# Extracts set terms
|
14
|
+
def extractSetTerms(to_extract, extract_term_fields, case_sensitive)
|
15
|
+
@input.each do |item|
|
16
|
+
extract = ExtractSetTerms.new(item, @extract_from, to_extract, extract_term_fields, case_sensitive, @save_field)
|
17
|
+
@output.push(extract.extractTerms)
|
18
|
+
end
|
19
|
+
end
|
20
|
+
|
21
|
+
# Gets all results in output
|
22
|
+
def getAllOutput
|
23
|
+
JSON.pretty_generate(@output)
|
24
|
+
end
|
25
|
+
|
26
|
+
# Gets only the results for which terms were found/extracted
|
27
|
+
def getOnlyMatching
|
28
|
+
matches = @output.select { |item| !item[@save_field].empty? }
|
29
|
+
JSON.pretty_generate(matches)
|
30
|
+
end
|
31
|
+
|
32
|
+
# Gets a list of the extracted terms by how often they occur
|
33
|
+
def getTermList
|
34
|
+
counthash = Hash.new{0}
|
35
|
+
|
36
|
+
# Increments for each occurrence of term
|
37
|
+
@output.each do |item|
|
38
|
+
item[@save_field].each do |term|
|
39
|
+
counthash[term] += 1
|
40
|
+
end
|
41
|
+
end
|
42
|
+
|
43
|
+
# Return hash sorted by value
|
44
|
+
return Hash[counthash.sort_by { |k, v| v}]
|
45
|
+
end
|
46
|
+
end
|
metadata
ADDED
@@ -0,0 +1,45 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: termextractor
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.16
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- M. C. McGrath
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-04-20 00:00:00.000000000 Z
|
12
|
+
dependencies: []
|
13
|
+
description: Extracts entities and terms from any JSON.
|
14
|
+
email: shidash@shidash.com
|
15
|
+
executables: []
|
16
|
+
extensions: []
|
17
|
+
extra_rdoc_files: []
|
18
|
+
files:
|
19
|
+
- lib/extract_set_terms.rb
|
20
|
+
- lib/term_extractor.rb
|
21
|
+
homepage: https://github.com/Shidash/EntityExtractor
|
22
|
+
licenses:
|
23
|
+
- GPL
|
24
|
+
metadata: {}
|
25
|
+
post_install_message:
|
26
|
+
rdoc_options: []
|
27
|
+
require_paths:
|
28
|
+
- lib
|
29
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
35
|
+
requirements:
|
36
|
+
- - ">="
|
37
|
+
- !ruby/object:Gem::Version
|
38
|
+
version: '0'
|
39
|
+
requirements: []
|
40
|
+
rubyforge_project:
|
41
|
+
rubygems_version: 2.2.2
|
42
|
+
signing_key:
|
43
|
+
specification_version: 4
|
44
|
+
summary: Extracts entities and terms
|
45
|
+
test_files: []
|