wordcloud 0.0.3 → 0.0.4
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.
- data/lib/wordcloud.rb +49 -17
- metadata +2 -2
data/lib/wordcloud.rb
CHANGED
@@ -1,30 +1,48 @@
|
|
1
|
+
require 'json'
|
2
|
+
|
1
3
|
class WordCloud
|
2
4
|
def initialize(input)
|
3
|
-
@input = input
|
5
|
+
@input = JSON.parse(input)
|
4
6
|
@output = ""
|
5
7
|
@wordhash = Hash.new
|
6
8
|
end
|
7
9
|
|
8
10
|
# Splits corpus on words
|
9
|
-
def parse
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
11
|
+
def parse
|
12
|
+
docnum = 0
|
13
|
+
@input.each do |i|
|
14
|
+
i.each do |j|
|
15
|
+
splitinput = j[1].split(" ")
|
16
|
+
splitinput.each do |w|
|
17
|
+
if w.include? "\\n"
|
18
|
+
w.gsub!("\\n", "<br />")
|
19
|
+
end
|
20
|
+
wordCount(w)
|
21
|
+
end
|
15
22
|
end
|
16
|
-
|
23
|
+
docnum += 1
|
17
24
|
end
|
18
25
|
|
19
|
-
|
26
|
+
@input.each do |i|
|
27
|
+
i.each do |j|
|
28
|
+
@output = @output + "<b>" + j[0] + ": " + "</b>" + genOutput(j[1], docnum) + "<br />"
|
29
|
+
end
|
30
|
+
@output = @output + "<br />"
|
31
|
+
end
|
20
32
|
return @output
|
21
33
|
end
|
22
34
|
|
23
35
|
# Counts number of times a word shows up
|
24
36
|
def wordCount(word)
|
25
|
-
commonwords = ["the", "and", "of", "a", "to", "is", "in", "its", "The", "on", "as", "for", "has", "will", "As", "or", "have", "while", "While", "that", "out", "such", "also", "by", "said", "with", "than", "only", "into", "an", "one", "other", "but", "for", "from", "<br />", "I", "more", "about", "About", "again", "Again", "against", "all", "are", "at", "be", "being", "been", "can", "could", "did", "do", "don't", "down", "up", "each", "few", "get", "got", "great", "had", "have", "has", "he", "her", "she", "he", "it", "we", "they", "if", "thus", "it's", "hers", "his", "how", "why", "when", "where", "just", "like", "you", "me", "my", "most", "more", "no", "not", "yes", "off", "once", "only", "our", "out", "over", "under", "own", "then", "some", "these", "there", "then", "this", "those", "too", "through", "between", "until", "very", "who", "with", "wouldn't", "would"]
|
37
|
+
commonwords = ["the", "and", "of", "a", "to", "is", "in", "its", "The", "on", "as", "for", "has", "will", "As", "or", "have", "while", "While", "that", "out", "such", "also", "by", "said", "with", "than", "only", "into", "an", "one", "other", "but", "for", "from", "<br />", "I", "more", "about", "About", "again", "Again", "against", "all", "are", "at", "be", "being", "been", "can", "could", "did", "do", "don't", "down", "up", "each", "few", "get", "got", "great", "had", "have", "has", "he", "her", "she", "he", "it", "we", "they", "if", "thus", "it's", "hers", "his", "how", "why", "when", "where", "just", "like", "you", "me", "my", "most", "more", "no", "not", "yes", "off", "once", "only", "our", "out", "over", "under", "own", "then", "some", "these", "there", "then", "this", "those", "too", "through", "between", "until", "very", "who", "with", "wouldn't", "would", "was", "were", "itself", "himself", "herself", "which", "make", "during", "before", "after", "if", "any", "become", "around", "several", "them", "their", "however"]
|
26
38
|
|
27
|
-
|
39
|
+
# Make capitalized array of common words
|
40
|
+
commoncaps = Array.new
|
41
|
+
commonwords.each do |c|
|
42
|
+
commoncaps.push(c.capitalize)
|
43
|
+
end
|
44
|
+
|
45
|
+
if (@wordhash[word]) && (!commonwords.include? word) && (!commoncaps.include? word)
|
28
46
|
@wordhash[word] += 1
|
29
47
|
else
|
30
48
|
@wordhash[word] = 1
|
@@ -32,19 +50,33 @@ class WordCloud
|
|
32
50
|
end
|
33
51
|
|
34
52
|
# Generates HTML output based on word size
|
35
|
-
def genOutput
|
36
|
-
splitinput =
|
53
|
+
def genOutput(input, docnum)
|
54
|
+
splitinput = input.split(/ /)
|
55
|
+
output = ""
|
37
56
|
|
38
57
|
splitinput.each do |w|
|
39
|
-
if w
|
40
|
-
w.gsub!(
|
58
|
+
if w =~ /\n/
|
59
|
+
w.gsub!(/\n/, "<br />")
|
41
60
|
end
|
42
61
|
|
43
62
|
if @wordhash[w]
|
44
|
-
size =
|
45
|
-
|
63
|
+
size = 10 + @wordhash[w]
|
64
|
+
if @wordhash[w] > 2
|
65
|
+
size = size - (docnum*0.1)
|
66
|
+
end
|
67
|
+
|
68
|
+
if size > 18
|
69
|
+
size = 18
|
70
|
+
output = output + " <span style=\"font-size:" + size.to_s + "px\"><b>" + w + "</b></span>"
|
71
|
+
else
|
72
|
+
output = output + " <span style=\"font-size:" + size.to_s + "px\">" + w + "</span>"
|
73
|
+
end
|
74
|
+
else
|
75
|
+
output = output + " " + w
|
46
76
|
end
|
47
77
|
end
|
78
|
+
|
79
|
+
return output
|
48
80
|
end
|
49
81
|
end
|
50
82
|
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: wordcloud
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.4
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,7 +9,7 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2014-
|
12
|
+
date: 2014-03-29 00:00:00.000000000 Z
|
13
13
|
dependencies: []
|
14
14
|
description: Takes input and outputs the same text with word size changed based on
|
15
15
|
frequency.
|