text_analyzer 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +15 -0
- data/lib/text_analyzer.rb +112 -0
- metadata +44 -0
checksums.yaml
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
---
|
2
|
+
!binary "U0hBMQ==":
|
3
|
+
metadata.gz: !binary |-
|
4
|
+
ZTMxNzI2NzkxZmI1ZjhlZWFmNjlhYjQ5ZDgwZjA0YTQyMDdlYTUzZA==
|
5
|
+
data.tar.gz: !binary |-
|
6
|
+
MjYwODdmODZhYjNhNGJjY2I2YmI4ZDA1NzBhYTA0MGQ5OWY1ZDdiNA==
|
7
|
+
!binary "U0hBNTEy":
|
8
|
+
metadata.gz: !binary |-
|
9
|
+
NGQ0OWM0NDM4MWQ3MGM5MjQyNjVhYjU2NmI4NmI1ZjZhNzUwM2MyODFiMzRh
|
10
|
+
MWE0NjQ3MjJlMzI0ZTZhZDk0ZDg3YjcwMGRmYmQwM2I0YzQxNmUwNzdiNjA4
|
11
|
+
MDYwNzdjMTg1NjA3NGU0YjU2ZTE5NWE3OTFlYTM0NDQ2YmY0MGE=
|
12
|
+
data.tar.gz: !binary |-
|
13
|
+
MzAxOWEzZDgxZjVhMWJkOTYzM2MyZjE1MTc4ZTFjODhhNTc5ZTM1MjllNGVh
|
14
|
+
MmUyODAyODg0NDRlZjQ1ODA3ZDYyNGIyMjQ1NzgzNDJlYTNlMTFjNzk3NDYx
|
15
|
+
YTZiYTZmNDM3YTFkMTNkMTAwNWY1NWQ5ZTE2YWRjOTliZTYzYzU=
|
@@ -0,0 +1,112 @@
|
|
1
|
+
class TextAnalyzer
|
2
|
+
attr_accessor :text
|
3
|
+
attr_reader :arr, :unique,:textaz, :zipped, :count
|
4
|
+
def initialize text
|
5
|
+
@text=text
|
6
|
+
@textaz
|
7
|
+
@arr
|
8
|
+
@unique
|
9
|
+
@zipped
|
10
|
+
@count
|
11
|
+
@hash
|
12
|
+
|
13
|
+
end
|
14
|
+
def init
|
15
|
+
get_words
|
16
|
+
slice_to_symbols
|
17
|
+
count_occurrences
|
18
|
+
sort_words
|
19
|
+
to_h
|
20
|
+
end
|
21
|
+
def get_words
|
22
|
+
@textaz=@text.downcase.gsub /[^a-z]/, ' ' #/[\.,\"]/, ' '
|
23
|
+
end
|
24
|
+
|
25
|
+
def slice_to_symbols
|
26
|
+
@textaz||=get_words
|
27
|
+
@arr=@textaz.split(' ').map{|x| x.to_sym}
|
28
|
+
return true
|
29
|
+
end
|
30
|
+
|
31
|
+
def count_occurrences
|
32
|
+
@unique = @arr.uniq
|
33
|
+
@count=@unique.map {|x| arr.count x}
|
34
|
+
# return @unique, @count
|
35
|
+
return true
|
36
|
+
end
|
37
|
+
def sort_words
|
38
|
+
@zipped = (@unique.zip @count).sort {|x, y| y[1]<=>x[1]}
|
39
|
+
@count = []
|
40
|
+
@unique = []
|
41
|
+
@zipped.each{|x| @unique << x[0] }
|
42
|
+
@zipped.each{|x| @count << x[1] }
|
43
|
+
#return @unique, @count, @zipped
|
44
|
+
return true
|
45
|
+
end
|
46
|
+
def to_h
|
47
|
+
@hash ||= Hash[@zipped]
|
48
|
+
end
|
49
|
+
def to_s
|
50
|
+
'done'
|
51
|
+
end
|
52
|
+
def == ob
|
53
|
+
@text==ob.text
|
54
|
+
end
|
55
|
+
|
56
|
+
def values_from_list quantity
|
57
|
+
@hash.values_at *@unique[0...quantity]
|
58
|
+
end
|
59
|
+
|
60
|
+
def quantity
|
61
|
+
@unique.length
|
62
|
+
end
|
63
|
+
|
64
|
+
def length
|
65
|
+
@arr.length
|
66
|
+
end
|
67
|
+
|
68
|
+
def percentage symbol
|
69
|
+
c = length
|
70
|
+
w = @hash[symbol]
|
71
|
+
return w.to_f/c
|
72
|
+
end
|
73
|
+
|
74
|
+
def percentages
|
75
|
+
per = []
|
76
|
+
@unique.each{|x| per<< (percentage x)}
|
77
|
+
Hash[@unique.zip per]
|
78
|
+
end
|
79
|
+
|
80
|
+
#adds 2 object and create new object
|
81
|
+
def + obj
|
82
|
+
|
83
|
+
#@text=text
|
84
|
+
#@textaz
|
85
|
+
#@arr
|
86
|
+
#@unique
|
87
|
+
#@zipped
|
88
|
+
#@count
|
89
|
+
#@hash
|
90
|
+
|
91
|
+
new=TextAnalyzer.new @text+"\n"+obj.text
|
92
|
+
new.instance_variable_set(:@textaz, @textaz+"\n"+obj.textaz)
|
93
|
+
|
94
|
+
arr=@arr+obj.arr
|
95
|
+
new.instance_variable_set(:@arr, arr)
|
96
|
+
|
97
|
+
|
98
|
+
u=arr.uniq
|
99
|
+
c=u.map {|x| arr.count x}
|
100
|
+
zipped = (u.zip c).sort {|x, y| y[1]<=>x[1]}
|
101
|
+
u=c=[]
|
102
|
+
zipped.each{|x| u << x[0];c << x[1] }
|
103
|
+
#zipped.each{|x| c << x[1] }
|
104
|
+
new.instance_variable_set(:@unique, u)
|
105
|
+
new.instance_variable_set(:@count, c)
|
106
|
+
new.instance_variable_set(:@zipped, zipped)
|
107
|
+
new.instance_variable_set(:@hash, Hash[zipped])
|
108
|
+
|
109
|
+
|
110
|
+
return new
|
111
|
+
end
|
112
|
+
end
|
metadata
ADDED
@@ -0,0 +1,44 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: text_analyzer
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Darek Nędza
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2012-07-11 00:00:00.000000000 Z
|
12
|
+
dependencies: []
|
13
|
+
description: This simple text analyzer. It aimed at simplicity and not too much dependencies.
|
14
|
+
email: nedzadarek@gmail.com
|
15
|
+
executables: []
|
16
|
+
extensions: []
|
17
|
+
extra_rdoc_files: []
|
18
|
+
files:
|
19
|
+
- lib/text_analyzer.rb
|
20
|
+
homepage:
|
21
|
+
licenses: []
|
22
|
+
metadata: {}
|
23
|
+
post_install_message:
|
24
|
+
rdoc_options: []
|
25
|
+
require_paths:
|
26
|
+
- lib
|
27
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
28
|
+
requirements:
|
29
|
+
- - ! '>='
|
30
|
+
- !ruby/object:Gem::Version
|
31
|
+
version: '0'
|
32
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
33
|
+
requirements:
|
34
|
+
- - ! '>='
|
35
|
+
- !ruby/object:Gem::Version
|
36
|
+
version: '0'
|
37
|
+
requirements: []
|
38
|
+
rubyforge_project:
|
39
|
+
rubygems_version: 2.0.6
|
40
|
+
signing_key:
|
41
|
+
specification_version: 4
|
42
|
+
summary: A simple text analyzer
|
43
|
+
test_files: []
|
44
|
+
has_rdoc:
|