preadly-bulbasaur 0.6.1 → 0.7.0

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 CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA1:
3
- metadata.gz: 40b514207389a8d48e89d57e1368bdf5c05db0dd
4
- data.tar.gz: 8ec55684674c1587f0a6ecf7a1d851a182683977
3
+ metadata.gz: 0dc0a73c1850ae685cf72ca24ef60eb89f72b28e
4
+ data.tar.gz: 82073826c2a3eae44106a25afdc82c16cf6ec853
5
5
  SHA512:
6
- metadata.gz: 27980ae974932ced7c96047c3f4811df95d54fea82d481776b43f933a2979f3ed736fa2aab25fa378632a7040f762019677688a9ef3bce0c93e9d8d1d2eceab0
7
- data.tar.gz: 64a1c0ccfd39f8bfe3d68bda43a28d8518741cfbc5107fbcc5060ad79e6fc8d45be734384b1dff7c041fa6317d1f8e8497c0964ac987cbbdc5064f434042dbca
6
+ metadata.gz: eb0a1cf64c3eb6f738b37e9ee54814c544fe69447053145ae6a8320ade4221dd7ac3b535cff41ae881c9eb662f3b200ad7b157a6750d975251eb2d529b679196
7
+ data.tar.gz: a75600ad921fad3dd30e56c5fa0e47ce2efba244a5c49b8d12523c1696fa42da23d9f6328ad96eff88e43dfe746a1a762f66b202d8e1c0a83d59c01e76da3da0
@@ -0,0 +1,14 @@
1
+ module Bulbasaur
2
+ class RemoveAttributes
3
+ def initialize(html, banned_attrs)
4
+ @html = html
5
+ @banned_attrs = banned_attrs
6
+ end
7
+
8
+ def call
9
+ parsed_html = Nokogiri::HTML::DocumentFragment.parse @html
10
+ @banned_attrs.each { |attr| parsed_html.xpath(".//@#{attr}").remove }
11
+ parsed_html.to_s
12
+ end
13
+ end
14
+ end
@@ -0,0 +1,14 @@
1
+ module Bulbasaur
2
+ class RemoveTags
3
+ def initialize(html, banned_tags)
4
+ @html = html
5
+ @banned_tags = banned_tags
6
+ end
7
+
8
+ def call
9
+ parsed_html = Nokogiri::HTML::DocumentFragment.parse @html
10
+ @banned_tags.each { |tag| parsed_html.css(tag).remove }
11
+ parsed_html.to_s
12
+ end
13
+ end
14
+ end
@@ -0,0 +1,32 @@
1
+ module Bulbasaur
2
+ class NormalizeImageSources
3
+ def initialize(html, target_attrs)
4
+ @html = html
5
+ @target_attrs = target_attrs
6
+ end
7
+
8
+ def call
9
+ parsed_html = Nokogiri::HTML::DocumentFragment.parse @html
10
+ parsed_html.css('img').each do |element|
11
+ check_for_attrs element
12
+ end
13
+ parsed_html.to_s
14
+ end
15
+
16
+ private
17
+
18
+ def check_for_attrs(element)
19
+ @target_attrs.each do |attr|
20
+ if element.xpath "@#{attr}"
21
+ adjust element, "@#{attr}"
22
+ break
23
+ end
24
+ end
25
+ end
26
+
27
+ def adjust(element, attr)
28
+ element.set_attribute 'src', element.xpath(attr).text
29
+ element.xpath(attr).remove
30
+ end
31
+ end
32
+ end
@@ -2,8 +2,8 @@ module Bulbasaur
2
2
 
3
3
  module Version
4
4
  MAJOR = 0
5
- MINOR = 6
6
- PATCH = 1
5
+ MINOR = 7
6
+ PATCH = 0
7
7
  STRING = "#{MAJOR}.#{MINOR}.#{PATCH}"
8
8
  end
9
9
 
data/lib/bulbasaur.rb CHANGED
@@ -4,8 +4,11 @@ require "bulbasaur/extracts/extract_images_from_vimeo"
4
4
  require "bulbasaur/extracts/extract_images_from_html"
5
5
  require "bulbasaur/extracts/extract_images_from_all_resources"
6
6
  require "bulbasaur/extracts/extract_text_from_html.rb"
7
+ require "bulbasaur/removals/remove_tags"
8
+ require "bulbasaur/removals/remove_attributes"
7
9
  require "bulbasaur/replaces/replace_by_tag_image"
8
10
  require "bulbasaur/utils/normalize_url"
11
+ require "bulbasaur/utils/normalize_image_sources"
9
12
  require "bulbasaur/version"
10
13
 
11
14
 
@@ -0,0 +1,45 @@
1
+ require 'spec_helper'
2
+
3
+ RSpec.describe Bulbasaur::RemoveAttributes do
4
+ subject { described_class.new(html, banned_attrs).call }
5
+
6
+ describe '#call' do
7
+ let(:html) do
8
+ %[
9
+ <style>
10
+ div { color: green; width: 1024px; }
11
+ </style>
12
+ <div style="height: 100px; width: 100px;"></div>
13
+ <form>
14
+ <input type="text">
15
+ </form>
16
+ <p style="font-size: x-large">hello!</p>
17
+ ]
18
+ end
19
+
20
+ context 'when there are no banned attributes' do
21
+ let(:banned_attrs) { [] }
22
+
23
+ it 'returns the HTML code as it was before' do
24
+ expect(subject).to eq html
25
+ end
26
+ end
27
+
28
+ context 'when there are banned attributes' do
29
+ let(:banned_attrs) { %w(style) }
30
+
31
+ it 'returns the HTML code without the banned attributes' do
32
+ expect(subject.strip.gsub(/\n/, '').squeeze ' ').to eq %[
33
+ <style>
34
+ div { color: green; width: 1024px; }
35
+ </style>
36
+ <div></div>
37
+ <form>
38
+ <input type="text">
39
+ </form>
40
+ <p>hello!</p>
41
+ ].strip.gsub(/\n/, '').squeeze ' '
42
+ end
43
+ end
44
+ end
45
+ end
@@ -0,0 +1,39 @@
1
+ require 'spec_helper'
2
+
3
+ RSpec.describe Bulbasaur::RemoveTags do
4
+ subject { described_class.new(html, banned_tags).call }
5
+
6
+ describe '#call' do
7
+ let(:html) do
8
+ %[
9
+ <style>
10
+ div { color: green; width: 1024px; }
11
+ </style>
12
+ <div style="height: 100px; width: 100px;"></div>
13
+ <form>
14
+ <input type="text">
15
+ </form>
16
+ <p>hello!</p>
17
+ ]
18
+ end
19
+
20
+ context 'when there are no banned tags' do
21
+ let(:banned_tags) { [] }
22
+
23
+ it 'returns the HTML code as it was before' do
24
+ expect(subject).to eq html
25
+ end
26
+ end
27
+
28
+ context 'when there are banned tags' do
29
+ let(:banned_tags) { %w(form style) }
30
+
31
+ it 'returns the HTML code without the banned tags' do
32
+ expect(subject.strip.gsub(/\n/, '').squeeze ' ').to eq %[
33
+ <div style="height: 100px; width: 100px;"></div>
34
+ <p>hello!</p>
35
+ ].strip.gsub(/\n/, '').squeeze ' '
36
+ end
37
+ end
38
+ end
39
+ end
@@ -0,0 +1,25 @@
1
+ require 'spec_helper'
2
+
3
+ RSpec.describe Bulbasaur::NormalizeImageSources do
4
+ subject { described_class.new(html, target_attrs).call }
5
+
6
+ describe '#call' do
7
+ let(:html) { '<img src="http://somewhere.to/get/a-pixel.gif" data-lazy-src="http://somewhere.to/get/the-real-image.jpg" alt="Image" width="800" height="1200">' }
8
+
9
+ context 'when there are no target attributes' do
10
+ let(:target_attrs) { [] }
11
+
12
+ it 'returns the HTML code as it was before' do
13
+ expect(subject).to eq html
14
+ end
15
+ end
16
+
17
+ context 'when there are target attributes' do
18
+ let(:target_attrs) { %w(data-lazy-src) }
19
+
20
+ it 'returns the HTML code with the image tags adjusted' do
21
+ expect(subject).to eq '<img src="http://somewhere.to/get/the-real-image.jpg" alt="Image" width="800" height="1200">'
22
+ end
23
+ end
24
+ end
25
+ end
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: preadly-bulbasaur
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.6.1
4
+ version: 0.7.0
5
5
  platform: ruby
6
6
  authors:
7
7
  - Magno Costa
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2015-08-06 00:00:00.000000000 Z
11
+ date: 2015-08-07 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: bundler
@@ -95,7 +95,10 @@ files:
95
95
  - lib/bulbasaur/extracts/extract_images_from_vimeo.rb
96
96
  - lib/bulbasaur/extracts/extract_images_from_youtube.rb
97
97
  - lib/bulbasaur/extracts/extract_text_from_html.rb
98
+ - lib/bulbasaur/removals/remove_attributes.rb
99
+ - lib/bulbasaur/removals/remove_tags.rb
98
100
  - lib/bulbasaur/replaces/replace_by_tag_image.rb
101
+ - lib/bulbasaur/utils/normalize_image_sources.rb
99
102
  - lib/bulbasaur/utils/normalize_url.rb
100
103
  - lib/bulbasaur/version.rb
101
104
  - spec/bulbasaur/extracts/extract_images_from_all_resources_spec.rb
@@ -103,7 +106,10 @@ files:
103
106
  - spec/bulbasaur/extracts/extract_images_from_vimeo_spec.rb
104
107
  - spec/bulbasaur/extracts/extract_images_from_youtube_spec.rb
105
108
  - spec/bulbasaur/extracts/extract_inner_text_from_html_spec.rb
109
+ - spec/bulbasaur/removals/remove_attributes_spec.rb
110
+ - spec/bulbasaur/removals/remove_tags_spec.rb
106
111
  - spec/bulbasaur/replaces/replace_by_tag_image_spec.rb
112
+ - spec/bulbasaur/utils/normalize_image_sources_spec.rb
107
113
  - spec/bulbasaur/utils/normalize_url_spec.rb
108
114
  - spec/bulbasaur_spec.rb
109
115
  - spec/spec_helper.rb
@@ -136,7 +142,10 @@ test_files:
136
142
  - spec/bulbasaur/extracts/extract_images_from_vimeo_spec.rb
137
143
  - spec/bulbasaur/extracts/extract_images_from_youtube_spec.rb
138
144
  - spec/bulbasaur/extracts/extract_inner_text_from_html_spec.rb
145
+ - spec/bulbasaur/removals/remove_attributes_spec.rb
146
+ - spec/bulbasaur/removals/remove_tags_spec.rb
139
147
  - spec/bulbasaur/replaces/replace_by_tag_image_spec.rb
148
+ - spec/bulbasaur/utils/normalize_image_sources_spec.rb
140
149
  - spec/bulbasaur/utils/normalize_url_spec.rb
141
150
  - spec/bulbasaur_spec.rb
142
151
  - spec/spec_helper.rb