documentally 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/README.md +23 -0
- data/lib/documentally.rb +5 -0
- data/lib/documentally/corpus.rb +23 -0
- data/lib/documentally/document.rb +40 -0
- metadata +48 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: f7ba9de32ab5018f410bf3e823c9f8a219b52fc0
|
4
|
+
data.tar.gz: 723aba4f6bc91aaa0b8c189b4026af67b5bee329
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 1ed6ff89c2a3866d00289a21592b03ce14722730dbb1709ceb3a4d14549bfe3e3e2c74cfa71a2518b57c8944f27bf821766c5425fd34b231f85e1020a973832a
|
7
|
+
data.tar.gz: 7081161224242150f5d9cf2a15d31edfeb765bb6bdc8150e9328fb3316e9995bf8b2885e59f2aae438e9bd79909f237aa768eec4008f24504a50dddf6859f527
|
data/README.md
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
# Documentally
|
2
|
+
|
3
|
+
Documentally uses [TF-IDF](http://en.wikipedia.org/wiki/tf-idf) to allow you to easily search and compare text documents.
|
4
|
+
|
5
|
+
It's still under development, so the documentation is basically just the tests right now, but an example use would be:
|
6
|
+
|
7
|
+
```ruby
|
8
|
+
term_lists = [['doc_1', ['foo', 'foo', 'bar']],
|
9
|
+
['doc_2', ['bar', 'baz', 'baz']],
|
10
|
+
['doc_3', ['bar', 'baz', 'foo']]]
|
11
|
+
|
12
|
+
corpus = Documentally::Corpus.new(term_lists)
|
13
|
+
|
14
|
+
query = Documentally::Document.new('query', ['baz'])
|
15
|
+
|
16
|
+
corpus.search(query) # => ['doc_2']
|
17
|
+
```
|
18
|
+
|
19
|
+
## Installation
|
20
|
+
|
21
|
+
```sh
|
22
|
+
gem install documentally
|
23
|
+
```
|
data/lib/documentally.rb
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
class Documentally::Corpus
|
2
|
+
attr_reader :documents
|
3
|
+
|
4
|
+
def initialize(term_lists)
|
5
|
+
all_terms = term_lists.map(&:last).inject(&:+)
|
6
|
+
master_document = Documentally::Document.new('master', all_terms)
|
7
|
+
|
8
|
+
@documents = term_lists.map { |name, term_list| Documentally::Document.new(name, term_list) }
|
9
|
+
documents.each do |document|
|
10
|
+
document.normalize!(master_document)
|
11
|
+
end
|
12
|
+
end
|
13
|
+
|
14
|
+
def search(query, take: 1)
|
15
|
+
order_documents_by(query).take(take)
|
16
|
+
end
|
17
|
+
|
18
|
+
private
|
19
|
+
|
20
|
+
def order_documents_by(query)
|
21
|
+
documents.sort_by { |document| document.similarity(query) }.reverse
|
22
|
+
end
|
23
|
+
end
|
@@ -0,0 +1,40 @@
|
|
1
|
+
class Documentally::Document
|
2
|
+
attr_accessor :term_hash
|
3
|
+
attr_reader :name
|
4
|
+
|
5
|
+
def initialize(name, terms)
|
6
|
+
@name = name
|
7
|
+
@term_hash = Hash.new(0.0)
|
8
|
+
|
9
|
+
terms.each do |term|
|
10
|
+
@term_hash[term] += 1
|
11
|
+
end
|
12
|
+
end
|
13
|
+
|
14
|
+
def to_s
|
15
|
+
name.to_s
|
16
|
+
end
|
17
|
+
|
18
|
+
def terms
|
19
|
+
term_hash.keys
|
20
|
+
end
|
21
|
+
|
22
|
+
def frequency(term)
|
23
|
+
term_hash[term]
|
24
|
+
end
|
25
|
+
|
26
|
+
def ==(other)
|
27
|
+
union_of_terms = (terms + other.terms).uniq
|
28
|
+
union_of_terms.all? { |term| frequency(term) == other.frequency(term) }
|
29
|
+
end
|
30
|
+
|
31
|
+
def similarity(query)
|
32
|
+
terms.map { |term| frequency(term) * query.frequency(term) }.inject(&:+)
|
33
|
+
end
|
34
|
+
|
35
|
+
def normalize!(corpus)
|
36
|
+
terms.each do |term|
|
37
|
+
term_hash[term] /= corpus.frequency(term)
|
38
|
+
end
|
39
|
+
end
|
40
|
+
end
|
metadata
ADDED
@@ -0,0 +1,48 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: documentally
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Harry Schwartz
|
8
|
+
- Dan Honey
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2014-02-09 00:00:00.000000000 Z
|
13
|
+
dependencies: []
|
14
|
+
description:
|
15
|
+
email: hello@harryrschwartz.com
|
16
|
+
executables: []
|
17
|
+
extensions: []
|
18
|
+
extra_rdoc_files: []
|
19
|
+
files:
|
20
|
+
- README.md
|
21
|
+
- lib/documentally.rb
|
22
|
+
- lib/documentally/corpus.rb
|
23
|
+
- lib/documentally/document.rb
|
24
|
+
homepage: http://github.com/hrs/documentally
|
25
|
+
licenses:
|
26
|
+
- GPL
|
27
|
+
metadata: {}
|
28
|
+
post_install_message:
|
29
|
+
rdoc_options: []
|
30
|
+
require_paths:
|
31
|
+
- lib
|
32
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
33
|
+
requirements:
|
34
|
+
- - ">="
|
35
|
+
- !ruby/object:Gem::Version
|
36
|
+
version: '0'
|
37
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
38
|
+
requirements:
|
39
|
+
- - ">="
|
40
|
+
- !ruby/object:Gem::Version
|
41
|
+
version: '0'
|
42
|
+
requirements: []
|
43
|
+
rubyforge_project:
|
44
|
+
rubygems_version: 2.2.2
|
45
|
+
signing_key:
|
46
|
+
specification_version: 4
|
47
|
+
summary: Simple TF-IDF document search library.
|
48
|
+
test_files: []
|