html2text 0.2.0 → 0.4.0

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.
Files changed (29) hide show
  1. checksums.yaml +5 -13
  2. data/CHANGELOG.md +50 -0
  3. data/README.md +19 -14
  4. data/lib/html2text/version.rb +3 -1
  5. data/lib/html2text.rb +158 -69
  6. metadata +90 -73
  7. data/spec/examples/anchors.html +0 -12
  8. data/spec/examples/anchors.txt +0 -5
  9. data/spec/examples/basic.html +0 -21
  10. data/spec/examples/basic.txt +0 -13
  11. data/spec/examples/full_email.html +0 -220
  12. data/spec/examples/full_email.txt +0 -54
  13. data/spec/examples/images.html +0 -54
  14. data/spec/examples/images.txt +0 -27
  15. data/spec/examples/lists.html +0 -24
  16. data/spec/examples/lists.txt +0 -17
  17. data/spec/examples/more-anchors.html +0 -14
  18. data/spec/examples/more-anchors.txt +0 -7
  19. data/spec/examples/nbsp.html +0 -1
  20. data/spec/examples/nbsp.txt +0 -1
  21. data/spec/examples/table.html +0 -53
  22. data/spec/examples/table.txt +0 -7
  23. data/spec/examples/test3.html +0 -1
  24. data/spec/examples/test3.txt +0 -2
  25. data/spec/examples/test4.html +0 -1
  26. data/spec/examples/test4.txt +0 -5
  27. data/spec/examples_spec.rb +0 -29
  28. data/spec/html2text_spec.rb +0 -37
  29. data/spec/spec_helper.rb +0 -4
data/spec/examples/images.txt DELETED
@@ -1,27 +0,0 @@
1
- One:
2
-
3
- Two: [two]
4
-
5
- Three: [three]
6
-
7
- Four: [four]
8
-
9
- With links
10
-
11
- One: http://localhost
12
-
13
- Two: [two](http://localhost)
14
-
15
- Three: [three](http://localhost)
16
-
17
- Four: [four](http://localhost)
18
-
19
- With links with titles
20
-
21
- One: [one link](http://localhost)
22
-
23
- Two: [two link](http://localhost)
24
-
25
- Three: [three link](http://localhost)
26
-
27
- Four: [four link](http://localhost)
data/spec/examples/lists.html DELETED
@@ -1,24 +0,0 @@
1
- <h1>List tests</h1>
2
-
3
- <p>
4
- Add some lists.
5
- </p>
6
-
7
- <ol>
8
- <li>one</li>
9
- <li>two
10
- <li>three
11
- </ol>
12
-
13
- <h2>An unordered list</h2>
14
-
15
- <ul>
16
- <li>one
17
- <li>two</li>
18
- <li>three</li>
19
- </ul>
20
- <ul>
21
- <li>one
22
- <li>two</li>
23
- <li>three</li>
24
- </ul>
data/spec/examples/lists.txt DELETED
@@ -1,17 +0,0 @@
1
- List tests
2
-
3
- Add some lists.
4
-
5
- - one
6
- - two
7
- - three
8
-
9
- An unordered list
10
-
11
- - one
12
- - two
13
- - three
14
-
15
- - one
16
- - two
17
- - three
data/spec/examples/more-anchors.html DELETED
@@ -1,14 +0,0 @@
1
- <h1>Anchor tests</h1>
2
-
3
- <p>
4
- Visit http://openiaml.org or <a href="http://openiaml.org">openiaml.org</a> or <a href="http://openiaml.org">http://openiaml.org</a>.
5
- </p>
6
-
7
- <p>
8
- To visit with SSL, visit https://openiaml.org or <a href="https://openiaml.org">openiaml.org</a> or <a href="https://openiaml.org">https://openiaml.org</a>.
9
- </p>
10
-
11
- <p>
12
- To mail, email support@openiaml.org or mailto:support@openiaml.org
13
- or <a href="mailto:support@openiaml.org">support@openiaml.org</a> or <a href="mailto:support@openiaml.org">mailto:support@openiaml.org</a>.
14
- </p>
data/spec/examples/more-anchors.txt DELETED
@@ -1,7 +0,0 @@
1
- Anchor tests
2
-
3
- Visit http://openiaml.org or openiaml.org or http://openiaml.org.
4
-
5
- To visit with SSL, visit https://openiaml.org or openiaml.org or https://openiaml.org.
6
-
7
- To mail, email support@openiaml.org or mailto:support@openiaml.org or support@openiaml.org or mailto:support@openiaml.org.
data/spec/examples/nbsp.html DELETED
@@ -1 +0,0 @@
1
- hello &nbsp; world &amp; people &lt; &gt; &NBSP;
data/spec/examples/nbsp.txt DELETED
@@ -1 +0,0 @@
1
- hello world & people < > &NBSP;
data/spec/examples/table.html DELETED
@@ -1,53 +0,0 @@
1
- <html>
2
- <title>Ignored Title</title>
3
- <body>
4
- <h1>Hello, World!</h1>
5
- <table>
6
- <thead>
7
- <tr>
8
- <th>Col A</th>
9
- <th>Col B</th>
10
- </tr>
11
- </thead>
12
- <tbody>
13
- <tr>
14
- <td>
15
- Data A1
16
- </td>
17
- <td>
18
- Data B1
19
- </td>
20
- </tr>
21
- <tr>
22
- <td>
23
- Data A2
24
- </td>
25
- <td>
26
- Data B2
27
- </td>
28
- </tr>
29
- <tr>
30
- <td>
31
- Data A3
32
- </td>
33
- <td>
34
- Data B4
35
- </td>
36
- </tr>
37
- </tbody>
38
- <tfoot>
39
- <tr>
40
- <td>
41
- Total A
42
- </td>
43
- <td>
44
- Total B
45
- </td>
46
- </tr>
47
-
48
- </tfoot>
49
-
50
- </table>
51
-
52
- </body>
53
- </html>
data/spec/examples/table.txt DELETED
@@ -1,7 +0,0 @@
1
- Hello, World!
2
-
3
- Col A Col B
4
- Data A1 Data B1
5
- Data A2 Data B2
6
- Data A3 Data B4
7
- Total A Total B
data/spec/examples/test3.html DELETED
@@ -1 +0,0 @@
1
- test one<br />test two
data/spec/examples/test3.txt DELETED
@@ -1,2 +0,0 @@
1
- test one
2
- test two
data/spec/examples/test4.html DELETED
@@ -1 +0,0 @@
1
- 1<br />2<br />3<br />4<br />5 6
data/spec/examples/test4.txt DELETED
@@ -1,5 +0,0 @@
1
- 1
2
- 2
3
- 3
4
- 4
5
- 5 6
data/spec/examples_spec.rb DELETED
@@ -1,29 +0,0 @@
1
- require "spec_helper"
2
-
3
- describe Html2Text do
4
- describe "#convert" do
5
- let(:text) { Html2Text.convert(html) }
6
-
7
- examples = Dir[File.dirname(__FILE__) + "/examples/*.html"]
8
-
9
- examples.each do |filename|
10
- context "#{filename}" do
11
- let(:html) { File.read(filename) }
12
- let(:text_file) { filename.sub(".html", ".txt") }
13
- let(:expected) { Html2Text.fix_newlines(File.read(text_file)) }
14
-
15
- it "has an expected output" do
16
- expect(File.exist?(text_file)).to eq(true), "'#{text_file}' did not exist"
17
- end
18
-
19
- it "converts to text" do
20
- expect(text).to eq(expected)
21
- end
22
- end
23
- end
24
-
25
- it "has examples to test" do
26
- expect(examples.size).to_not eq(0)
27
- end
28
- end
29
- end
data/spec/html2text_spec.rb DELETED
@@ -1,37 +0,0 @@
1
- require "spec_helper"
2
-
3
- describe Html2Text do
4
- describe "#convert" do
5
- let(:text) { Html2Text.convert(html) }
6
-
7
- context "an empty line" do
8
- let(:html) { "" }
9
-
10
- it "is an empty line" do
11
- expect(text).to eq("")
12
- end
13
- end
14
-
15
- context "a simple string" do
16
- let(:html) { "hello world" }
17
-
18
- it "is an empty line" do
19
- expect(text).to eq("hello world")
20
- end
21
- end
22
- end
23
-
24
- describe "#remove_leading_and_trailing_whitespace" do
25
- let(:subject) { Html2Text.new(nil).remove_leading_and_trailing_whitespace(input) }
26
-
27
- context "an empty string" do
28
- let(:input) { "" }
29
- it { is_expected.to eq("") }
30
- end
31
-
32
- context "many new lines" do
33
- let(:input) { "hello\n world \n yes" }
34
- it { is_expected.to eq("hello\nworld\nyes") }
35
- end
36
- end
37
- end
data/spec/spec_helper.rb DELETED
@@ -1,4 +0,0 @@
1
- require "rspec"
2
- require "rspec/collection_matchers"
3
-
4
- require File.join(File.dirname(__FILE__), "..", "lib", "html2text")