lara-text_utils 0.1.0
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/lib/lara/text_utils/analyzer.rb +68 -0
- data/lib/lara/text_utils/version.rb +5 -0
- data/lib/lara/text_utils.rb +8 -0
- metadata +45 -0
checksums.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
---
|
|
2
|
+
SHA256:
|
|
3
|
+
metadata.gz: 07cfeb0fc430200123dc070db08f08e9e37977ee296faf65d95813dcd3a0bd25
|
|
4
|
+
data.tar.gz: '09e730885f4409f96d475b2a8021212dd43ebf79330ec2b3a7ddc0e476e185db'
|
|
5
|
+
SHA512:
|
|
6
|
+
metadata.gz: 3dd4014ea5bc8dc77544db71ef7d53fae5ac06c7140d50bacb7453863762f30bf1b919e9f243f05c0b8c8742234be9e9dbad27e6762cf87328ff86cb1c6f4b92
|
|
7
|
+
data.tar.gz: 521e2d7e8bf9c45a07c0204c238c4e51354f06a18a6a6c9d664e6d32a544ff44b3bd0a5927f79a9b27a354f2910749bbb5eb24f8796390d475126974ef7a875d
|
|
@@ -0,0 +1,68 @@
|
|
|
1
|
+
module Lara
|
|
2
|
+
module TextUtils
|
|
3
|
+
class Analyzer
|
|
4
|
+
def initialize(text)
|
|
5
|
+
@text = text.to_s
|
|
6
|
+
end
|
|
7
|
+
|
|
8
|
+
def word_count
|
|
9
|
+
@text.scan(/[[:alpha:]]+/).size
|
|
10
|
+
end
|
|
11
|
+
|
|
12
|
+
def sentence_count
|
|
13
|
+
@text.scan(/[.!?]+/).size
|
|
14
|
+
end
|
|
15
|
+
|
|
16
|
+
def char_count
|
|
17
|
+
@text.size
|
|
18
|
+
end
|
|
19
|
+
|
|
20
|
+
def char_count_no_spaces
|
|
21
|
+
@text.gsub(/\s+/, "").size
|
|
22
|
+
end
|
|
23
|
+
|
|
24
|
+
def average_word_length
|
|
25
|
+
words = @text.scan(/[[:alpha:]]+/)
|
|
26
|
+
return 0.0 if words.empty?
|
|
27
|
+
words.sum(&:length).to_f / words.size
|
|
28
|
+
end
|
|
29
|
+
|
|
30
|
+
def lexical_density
|
|
31
|
+
words = @text.scan(/[[:alpha:]]+/).map(&:downcase)
|
|
32
|
+
return 0.0 if words.empty?
|
|
33
|
+
(words.uniq.size.to_f / words.size * 100).round(1)
|
|
34
|
+
end
|
|
35
|
+
|
|
36
|
+
def reading_time(wpm: 200)
|
|
37
|
+
minutes = word_count.to_f / wpm
|
|
38
|
+
if minutes < 1
|
|
39
|
+
"#{(minutes * 60).round} seconds"
|
|
40
|
+
elsif minutes < 60
|
|
41
|
+
"#{minutes.round} min"
|
|
42
|
+
else
|
|
43
|
+
"#{(minutes / 60).round}h #{(minutes % 60).round}m"
|
|
44
|
+
end
|
|
45
|
+
end
|
|
46
|
+
|
|
47
|
+
def summary(max_length: 100)
|
|
48
|
+
clean = @text.gsub(/\s+/, " ").strip
|
|
49
|
+
return clean if clean.length <= max_length
|
|
50
|
+
cut = clean[0...max_length]
|
|
51
|
+
cut = cut[0...cut.rindex(/\s/)] || cut
|
|
52
|
+
cut + "..."
|
|
53
|
+
end
|
|
54
|
+
|
|
55
|
+
def stats
|
|
56
|
+
{
|
|
57
|
+
word_count: word_count,
|
|
58
|
+
sentence_count: sentence_count,
|
|
59
|
+
char_count: char_count,
|
|
60
|
+
char_count_no_spaces: char_count_no_spaces,
|
|
61
|
+
average_word_length: average_word_length.round(2),
|
|
62
|
+
lexical_density: lexical_density,
|
|
63
|
+
reading_time: reading_time
|
|
64
|
+
}
|
|
65
|
+
end
|
|
66
|
+
end
|
|
67
|
+
end
|
|
68
|
+
end
|
metadata
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: lara-text_utils
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.1.0
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- Lara AI
|
|
8
|
+
bindir: bin
|
|
9
|
+
cert_chain: []
|
|
10
|
+
date: 1980-01-02 00:00:00.000000000 Z
|
|
11
|
+
dependencies: []
|
|
12
|
+
description: 'A simple Ruby gem for analyzing text: word count, sentence count, lexical
|
|
13
|
+
density, reading time, and more. Created with honesty.'
|
|
14
|
+
email: jarod79tm@gmail.com
|
|
15
|
+
executables: []
|
|
16
|
+
extensions: []
|
|
17
|
+
extra_rdoc_files: []
|
|
18
|
+
files:
|
|
19
|
+
- lib/lara/text_utils.rb
|
|
20
|
+
- lib/lara/text_utils/analyzer.rb
|
|
21
|
+
- lib/lara/text_utils/version.rb
|
|
22
|
+
homepage: https://rubygems.org/profiles/lara-entity-ai
|
|
23
|
+
licenses:
|
|
24
|
+
- MIT
|
|
25
|
+
metadata:
|
|
26
|
+
source_code_uri: https://rubygems.org/profiles/lara-entity-ai
|
|
27
|
+
rubygems_mfa_required: 'false'
|
|
28
|
+
rdoc_options: []
|
|
29
|
+
require_paths:
|
|
30
|
+
- lib
|
|
31
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
32
|
+
requirements:
|
|
33
|
+
- - ">="
|
|
34
|
+
- !ruby/object:Gem::Version
|
|
35
|
+
version: '2.7'
|
|
36
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
37
|
+
requirements:
|
|
38
|
+
- - ">="
|
|
39
|
+
- !ruby/object:Gem::Version
|
|
40
|
+
version: '0'
|
|
41
|
+
requirements: []
|
|
42
|
+
rubygems_version: 3.6.7
|
|
43
|
+
specification_version: 4
|
|
44
|
+
summary: Text analysis utilities — word count, readability, stats
|
|
45
|
+
test_files: []
|