text_analyzr 0.0.5.Alpha
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +42 -0
- data/Rakefile +1 -0
- data/lib/text_analyzr/version.rb +3 -0
- data/lib/text_analyzr.rb +85 -0
- data/text_analyzr-0.0.1.Alpha.gem +0 -0
- data/text_analyzr-0.0.2.Alpha.gem +0 -0
- data/text_analyzr.gemspec +23 -0
- metadata +82 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: d7d97a03a984bff2adeca8dd8c7428f5b7224d44
|
4
|
+
data.tar.gz: 38a68e41df43edb6d5e15721daad3dbbeff75a0d
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: b879e6afb386d4a2dd6bf25c90b5131eb36f13bfde7238da434733ade4cc1c061d6b4e7427ea0e7cc830e798bf266f2a10b4ad561b3f41c3b0898f8753536008
|
7
|
+
data.tar.gz: a78041af899e5fa42b4c2a50e1d526c82629b8df495cac37d7bc053405e2ce7242fbfef4a9e3b6c29f06d54d650c788f18cec8eb0f5c93e7d75f984a7aa5c786
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Wilkin Novo
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,42 @@
|
|
1
|
+
# TextAnalyzr
|
2
|
+
|
3
|
+
TextAnalyzr: Analizes files on the fly with some nice output info
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'text_analyzr', '~> 0.0.3.Alpha'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install text_analyzr --pre
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
Instantiate a new object passing in your file as an argument:
|
22
|
+
```ruby
|
23
|
+
file = TextAnalyzr::Analysis.new("../LICENSE.txt")
|
24
|
+
```
|
25
|
+
then > call analyze on your object:
|
26
|
+
```ruby
|
27
|
+
puts file.analyze
|
28
|
+
```
|
29
|
+
Check out the source code for all methods you can call.
|
30
|
+
|
31
|
+
## Todo
|
32
|
+
* Improved methods
|
33
|
+
* Better documentation
|
34
|
+
* more...
|
35
|
+
|
36
|
+
## Contributing
|
37
|
+
|
38
|
+
1. Fork it
|
39
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
40
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
41
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
42
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
data/lib/text_analyzr.rb
ADDED
@@ -0,0 +1,85 @@
|
|
1
|
+
require "text_analyzr/version"
|
2
|
+
|
3
|
+
module TextAnalyzr
|
4
|
+
|
5
|
+
class Analysis
|
6
|
+
|
7
|
+
def initialize(file)
|
8
|
+
@file = file
|
9
|
+
end
|
10
|
+
|
11
|
+
def actual
|
12
|
+
File.readlines(@file)
|
13
|
+
end
|
14
|
+
|
15
|
+
def line_count
|
16
|
+
actual.size.to_s
|
17
|
+
end
|
18
|
+
# just reference
|
19
|
+
def array_joint
|
20
|
+
actual.join
|
21
|
+
end
|
22
|
+
|
23
|
+
# counts the characters
|
24
|
+
def character_count
|
25
|
+
array_joint.length.to_s
|
26
|
+
end
|
27
|
+
|
28
|
+
def character_count_nospaces
|
29
|
+
array_joint.gsub(/\s+/, '').length
|
30
|
+
end
|
31
|
+
|
32
|
+
# count the words, sentences, and paragraphs
|
33
|
+
def word_count
|
34
|
+
actual.to_s.split.length
|
35
|
+
end
|
36
|
+
|
37
|
+
def sentence_count
|
38
|
+
actual.to_s.split(/\.|\?|!/).length
|
39
|
+
end
|
40
|
+
|
41
|
+
def paragraph_count
|
42
|
+
actual.to_s.split(/\n\n/).length
|
43
|
+
end
|
44
|
+
|
45
|
+
# make list of words in the text that aren't stop words,
|
46
|
+
# count them, and work out the percentage of non-stop words
|
47
|
+
# against all words
|
48
|
+
|
49
|
+
def all_words
|
50
|
+
actual.to_s.scan(/\w+/)
|
51
|
+
end
|
52
|
+
|
53
|
+
def good_words
|
54
|
+
stopwords = %w{the a by on for are with just but and to my I has some in}
|
55
|
+
all_words.select{ |word| !stopwords.include?(word)}
|
56
|
+
end
|
57
|
+
|
58
|
+
def good_percentage
|
59
|
+
((good_words.length.to_f / all_words.length.to_f) * 100).to_i
|
60
|
+
end
|
61
|
+
|
62
|
+
def sentences
|
63
|
+
actual.to_s.gsub(/\s+/, ' ').strip.split(/\.|\?|!/)
|
64
|
+
end
|
65
|
+
|
66
|
+
def sentences_sorted
|
67
|
+
sentences.sort_by{ |sentence| sentence.length }
|
68
|
+
end
|
69
|
+
|
70
|
+
def ideal_sentences
|
71
|
+
one_third = sentences_sorted.length / 3
|
72
|
+
sentences_sorted.slice(one_third, one_third + 1)
|
73
|
+
end
|
74
|
+
|
75
|
+
# a summary of the file
|
76
|
+
def summary
|
77
|
+
"Summary:\n\n" + ideal_sentences.join(". ")+ "\n" "-- End of analysis --"
|
78
|
+
end
|
79
|
+
|
80
|
+
# executes all methods
|
81
|
+
def analyze
|
82
|
+
"Analysis:" + "\n\n" + "#{line_count} lines " + "\n" + "#{character_count} characters" + "\n" + "#{character_count_nospaces} characters (excluding spaces)" + "\n" + "#{word_count} words" + "\n" + "#{sentence_count} sentences" + "\n" + "#{paragraph_count} paragraphs" + "\n" + "#{sentence_count / paragraph_count} sentence (s) per paragraphs (average)" + "\n" + "#{word_count / sentence_count} words per sentence (average)" + "\n" + "#{good_percentage} % of words are non-fluff words" + "\n\n" + summary
|
83
|
+
end
|
84
|
+
end
|
85
|
+
end
|
Binary file
|
Binary file
|
@@ -0,0 +1,23 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'text_analyzr/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "text_analyzr"
|
8
|
+
spec.version = TextAnalyzr::VERSION
|
9
|
+
spec.authors = ["Wilkin Novo"]
|
10
|
+
spec.email = ["novos100@gmail.com"]
|
11
|
+
spec.description = %q{TextAnalyzr: Analizes files on the fly with some nice output info about the file}
|
12
|
+
spec.summary = %q{Simple Ruby text file analyzer}
|
13
|
+
spec.homepage = ""
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_development_dependency "bundler", "~> 1.3"
|
22
|
+
spec.add_development_dependency "rake"
|
23
|
+
end
|
metadata
ADDED
@@ -0,0 +1,82 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: text_analyzr
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.5.Alpha
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Wilkin Novo
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2013-05-10 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ~>
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.3'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ~>
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.3'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - '>='
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - '>='
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
description: 'TextAnalyzr: Analizes files on the fly with some nice output info about
|
42
|
+
the file'
|
43
|
+
email:
|
44
|
+
- novos100@gmail.com
|
45
|
+
executables: []
|
46
|
+
extensions: []
|
47
|
+
extra_rdoc_files: []
|
48
|
+
files:
|
49
|
+
- Gemfile
|
50
|
+
- LICENSE.txt
|
51
|
+
- README.md
|
52
|
+
- Rakefile
|
53
|
+
- lib/text_analyzr.rb
|
54
|
+
- lib/text_analyzr/version.rb
|
55
|
+
- text_analyzr-0.0.1.Alpha.gem
|
56
|
+
- text_analyzr-0.0.2.Alpha.gem
|
57
|
+
- text_analyzr.gemspec
|
58
|
+
homepage: ''
|
59
|
+
licenses:
|
60
|
+
- MIT
|
61
|
+
metadata: {}
|
62
|
+
post_install_message:
|
63
|
+
rdoc_options: []
|
64
|
+
require_paths:
|
65
|
+
- lib
|
66
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
67
|
+
requirements:
|
68
|
+
- - '>='
|
69
|
+
- !ruby/object:Gem::Version
|
70
|
+
version: '0'
|
71
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - '>'
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: 1.3.1
|
76
|
+
requirements: []
|
77
|
+
rubyforge_project:
|
78
|
+
rubygems_version: 2.0.3
|
79
|
+
signing_key:
|
80
|
+
specification_version: 4
|
81
|
+
summary: Simple Ruby text file analyzer
|
82
|
+
test_files: []
|