comparateur 1.0.2 → 2.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +50 -9
- data/examples/a.rb +48 -0
- data/lib/comparateur.rb +33 -10
- data/lib/comparateur/version.rb +1 -1
- metadata +3 -3
- data/a.rb +0 -11
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 3396baff4b80834299a15ffabeb73748ef16c6f5
|
4
|
+
data.tar.gz: 9d1fca09a2658a2c3ac0de11f29846040744d912
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 13e9616ca619fd82cdbfe5f1625663a0da7fd9a72bf1a1cbf9f70ff18e481773b6963e3cdafa5c3399decca0aa4bacfae47f0decdc2af652ab45dbc77b3163df
|
7
|
+
data.tar.gz: df66d064b6d2446d47225c381c64a37e395196fedba86e0b6af0e4941074e5acca107369ba7a5e1a497c13b7594f65546c75153f8f7c894dc932ed04c5ef663c
|
data/README.md
CHANGED
@@ -1,6 +1,17 @@
|
|
1
1
|
# Comparateur
|
2
2
|
|
3
|
-
|
3
|
+
[![Gem Version](https://badge.fury.io/rb/comparateur.svg)](http://badge.fury.io/rb/comparateur) [![comparateur Downloads](http://www.gemetric.me/images/comparateur.gif)](https://rubygems.org/gems/comparateur)
|
4
|
+
|
5
|
+
Calculate the structural similarity between two HTML documents.
|
6
|
+
|
7
|
+
**How it works**
|
8
|
+
It serializes strings, Nokogiri::HTML objects and URLs to arrays containing node's tag names and finds the longest common sequence between two serialized arrays.
|
9
|
+
|
10
|
+
The similarity is measured with the formula:
|
11
|
+
`2 * length(LCS Array) / (length(TreeA) + length(treeB))`
|
12
|
+
|
13
|
+
**How is done**
|
14
|
+
Classes are about objects and Modules are about functions. That's why you have to create a class and `include` or `extend` it with `Comparateur` and use it as you like. This implementation also let you built your own cache system.
|
4
15
|
|
5
16
|
## Installation
|
6
17
|
|
@@ -21,18 +32,48 @@ Or install it yourself as:
|
|
21
32
|
```ruby
|
22
33
|
require 'comparateur'
|
23
34
|
|
24
|
-
|
35
|
+
class LeComparateur
|
36
|
+
extend Comparateur
|
37
|
+
end
|
25
38
|
|
26
|
-
|
27
|
-
|
39
|
+
google_url = "http://google.com"
|
40
|
+
duckduck_url = "https://duckduckgo.com"
|
28
41
|
|
29
|
-
|
30
|
-
d = a
|
31
|
-
|
32
|
-
p exp.calculate_similarity(a, b) * 100 # in %
|
33
|
-
p exp.calculate_similarity(c, d)
|
42
|
+
LeComparateur.compare_urls(google_url, duckduck_url) # 0.3815789473684211
|
34
43
|
```
|
35
44
|
|
45
|
+
Example of usage [here](https://raw.githubusercontent.com/radubogdan/ruby-comparateur/master/examples/a.rb)
|
46
|
+
|
47
|
+
## Methods
|
48
|
+
|
49
|
+
`serialize_nokogiri_html(obj1)`
|
50
|
+
- `obj1`: Nokogiri::HTML object.
|
51
|
+
- `return`: Array containing node's tag names.
|
52
|
+
|
53
|
+
`serialize_url(url)`
|
54
|
+
- `url`: URL of the website.
|
55
|
+
- `return`: Array containing node's tag names.
|
56
|
+
|
57
|
+
`serialize_content(str)`
|
58
|
+
- `str`: String containing the html.
|
59
|
+
- `return`: Array containing node's tag names.
|
60
|
+
|
61
|
+
`compare_nokogiri_html(nok1, nok2)`
|
62
|
+
- `nok1, nok2`: Nokogiri::HTML objects.
|
63
|
+
- `return`: Score (0-1).
|
64
|
+
|
65
|
+
`compare_urls(url1, url2)`
|
66
|
+
- `url1, url2`: URL of two different websites.
|
67
|
+
- `return`: Score (0-1).
|
68
|
+
|
69
|
+
`compare_content(str1, str2)`
|
70
|
+
- `str1, str2`: First and second string which contain the html.
|
71
|
+
- `return`: Score (0-1).
|
72
|
+
|
73
|
+
`lcs(arr1, arr2)`
|
74
|
+
- `arr1, arr2`: First and second array which contain the node's tag names.
|
75
|
+
- `return`: Score (0-1)
|
76
|
+
|
36
77
|
## Contributing
|
37
78
|
|
38
79
|
1. Fork it ( https://github.com/radubogdan/ruby-comparateur/fork )
|
data/examples/a.rb
ADDED
@@ -0,0 +1,48 @@
|
|
1
|
+
load "./lib/comparateur.rb" # use require comparateur
|
2
|
+
|
3
|
+
# Create your own class and add
|
4
|
+
# Comparateur's functions as class methods
|
5
|
+
class LeComparateur
|
6
|
+
extend Comparateur
|
7
|
+
end
|
8
|
+
|
9
|
+
# Create your class and include all
|
10
|
+
# functions as instance methods
|
11
|
+
class MyClass
|
12
|
+
include Comparateur
|
13
|
+
end
|
14
|
+
|
15
|
+
# All examples use these
|
16
|
+
a = "<html><body><ul><li><ul><li></li></ul></li></ul></body></html"
|
17
|
+
b = "<html><body><ul><li></li></ul></body></html"
|
18
|
+
google_url = "http://google.com"
|
19
|
+
duckduck_url = "https://duckduckgo.com"
|
20
|
+
a_nok = Nokogiri::HTML(a)
|
21
|
+
b_nok = Nokogiri::HTML(b)
|
22
|
+
a_arr = %w(html body ul li ul li)
|
23
|
+
b_arr = %w(html body ul li)
|
24
|
+
|
25
|
+
# Serialize Nokogiri::HTML objects
|
26
|
+
# return: Array of HTML nodes
|
27
|
+
LeComparateur.serialize_nokogiri_html(a_nok) # ["html", "body", "ul", "li", "ul", "li"]
|
28
|
+
|
29
|
+
# Serialize URL
|
30
|
+
# return: Array of HTML nodes
|
31
|
+
LeComparateur.serialize_url(google_url) # Long array of nodes used in google.com
|
32
|
+
|
33
|
+
# Serialize Content
|
34
|
+
# return: Array of HTML nodes
|
35
|
+
LeComparateur.serialize_content(a) # ["html", "body", "ul", "li", "ul", "li"]
|
36
|
+
LeComparateur.serialize_content(b) # ["html", "body", "ul", "li"]
|
37
|
+
|
38
|
+
# Compare Nokogiri::HTML objects
|
39
|
+
LeComparateur.compare_nokogiri_html(a_nok, b_nok)
|
40
|
+
|
41
|
+
# Compare URLs
|
42
|
+
LeComparateur.compare_urls(google_url, duckduck_url) # 0.3815789473684211
|
43
|
+
|
44
|
+
# Compare content
|
45
|
+
LeComparateur.compare_content(a, b)
|
46
|
+
|
47
|
+
# Directly compare arrays of nodes
|
48
|
+
LeComparateur.lcs(a_arr, b_arr)
|
data/lib/comparateur.rb
CHANGED
@@ -1,20 +1,43 @@
|
|
1
1
|
require "comparateur/version"
|
2
2
|
require "nokogiri"
|
3
3
|
require "diff-lcs"
|
4
|
+
require "open-uri"
|
4
5
|
|
5
|
-
module
|
6
|
-
class Comparateur
|
6
|
+
module Comparateur
|
7
7
|
|
8
|
-
|
9
|
-
|
10
|
-
|
8
|
+
def serialize_nokogiri_html nokogiri_html
|
9
|
+
nokogiri_html.search('*').map(&:name)
|
10
|
+
end
|
11
|
+
|
12
|
+
def serialize_url url
|
13
|
+
Nokogiri::HTML(open(url)).search('*').map(&:name)
|
14
|
+
end
|
15
|
+
|
16
|
+
def serialize_content str
|
17
|
+
Nokogiri::HTML(str).search('*').map(&:name)
|
18
|
+
end
|
11
19
|
|
12
|
-
|
13
|
-
|
14
|
-
|
20
|
+
def compare_nokogiri_html nok1, nok2
|
21
|
+
s1 = serialize_nokogiri_html(nok1)
|
22
|
+
s2 = serialize_nokogiri_html(nok2)
|
23
|
+
lcs(s1, s2)
|
24
|
+
end
|
15
25
|
|
16
|
-
|
17
|
-
|
26
|
+
def compare_urls url1, url2
|
27
|
+
s1 = serialize_url(url1)
|
28
|
+
s2 = serialize_url(url2)
|
29
|
+
lcs(s1, s2)
|
30
|
+
end
|
18
31
|
|
32
|
+
def compare_content str1, str2
|
33
|
+
s1 = serialize_content(str1)
|
34
|
+
s2 = serialize_content(str2)
|
35
|
+
lcs(s1, s2)
|
19
36
|
end
|
37
|
+
|
38
|
+
def lcs arr1, arr2
|
39
|
+
lcs = Diff::LCS.LCS(arr1, arr2)
|
40
|
+
return (2.0 * lcs.length.to_f) / (arr1.length.to_f + arr2.length.to_f)
|
41
|
+
end
|
42
|
+
|
20
43
|
end
|
data/lib/comparateur/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: comparateur
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version:
|
4
|
+
version: 2.0.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Radu-Bogdan Croitoru
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2014-12-
|
11
|
+
date: 2014-12-06 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: nokogiri
|
@@ -78,8 +78,8 @@ files:
|
|
78
78
|
- LICENSE.txt
|
79
79
|
- README.md
|
80
80
|
- Rakefile
|
81
|
-
- a.rb
|
82
81
|
- comparateur.gemspec
|
82
|
+
- examples/a.rb
|
83
83
|
- lib/comparateur.rb
|
84
84
|
- lib/comparateur/version.rb
|
85
85
|
homepage: https://github.com/radubogdan/ruby-comparateur
|
data/a.rb
DELETED
@@ -1,11 +0,0 @@
|
|
1
|
-
load "lib/comparateur.rb"
|
2
|
-
|
3
|
-
exp = Le::Comparateur.new
|
4
|
-
|
5
|
-
#site1 = Nokogiri::HTML("<html><body><h1></h1><h2></h2></body></html>")
|
6
|
-
|
7
|
-
|
8
|
-
site1 = ["html", "body"]
|
9
|
-
site2 = Nokogiri::HTML("<html><body></body></html>")
|
10
|
-
|
11
|
-
p exp.calculate_similarity(site1, site2)
|