html_to_plain_text 1.0.4 → 1.0.5
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 +4 -4
- data/VERSION +1 -1
- data/lib/html_to_plain_text.rb +8 -2
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 2297205c53aeb650d7bacf92fd72e9d259fde896
|
4
|
+
data.tar.gz: dca3dc23d7916059863ded0b723d81df9384c818
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 5c6db32a927658696231f29604abafa19f11ccd1ec3b9085d687e4cb736cb64ad46fc3f364fb46c5f4c8c72d3d6485d3472baa0d0e1f9252ef6958b0e8d68aee
|
7
|
+
data.tar.gz: c737541bb924ecddbd202f07688d1963241893ed0c537d12714252c8aea69f101ebda69baaf7ac3dc13ab91c397b73d347cd64e799154b0d88b6283b286215de
|
data/VERSION
CHANGED
@@ -1 +1 @@
|
|
1
|
-
1.0.
|
1
|
+
1.0.5
|
data/lib/html_to_plain_text.rb
CHANGED
@@ -17,6 +17,7 @@ module HtmlToPlainText
|
|
17
17
|
UL = "ul".freeze
|
18
18
|
LI = "li".freeze
|
19
19
|
A = "a".freeze
|
20
|
+
TABLE = "table".freeze
|
20
21
|
NUMBERS = ["1", "a"].freeze
|
21
22
|
ABSOLUTE_URL_PATTERN = /^[a-z]+:\/\/[a-z0-9]/i.freeze
|
22
23
|
HTML_PATTERN = /[<&]/.freeze
|
@@ -30,6 +31,7 @@ module HtmlToPlainText
|
|
30
31
|
EMPTY = "".freeze
|
31
32
|
NEWLINE = "\n".freeze
|
32
33
|
HREF = "href".freeze
|
34
|
+
TABLE_SEPARATOR = " | ".freeze
|
33
35
|
|
34
36
|
# Helper instance method for converting HTML into plain text. This method simply calls HtmlToPlainText.plain_text.
|
35
37
|
def plain_text(html)
|
@@ -59,7 +61,7 @@ module HtmlToPlainText
|
|
59
61
|
end
|
60
62
|
|
61
63
|
format_list_item(out, options) if parent.name == LI
|
62
|
-
out << "| " if parent.name == TR
|
64
|
+
out << "| " if parent.name == TR && data_table?(parent.parent)
|
63
65
|
|
64
66
|
parent.children.each do |node|
|
65
67
|
if node.text? || node.cdata?
|
@@ -82,7 +84,7 @@ module HtmlToPlainText
|
|
82
84
|
out << NEWLINE unless out.end_with?(NEWLINE)
|
83
85
|
out << "-------------------------------\n"
|
84
86
|
elsif node.name == TD || node.name == TH
|
85
|
-
out <<
|
87
|
+
out << (data_table?(parent.parent) ? TABLE_SEPARATOR : SPACE)
|
86
88
|
elsif node.name == A
|
87
89
|
href = node[HREF]
|
88
90
|
if href &&
|
@@ -147,5 +149,9 @@ module HtmlToPlainText
|
|
147
149
|
out << "#{number}. "
|
148
150
|
end
|
149
151
|
end
|
152
|
+
|
153
|
+
def data_table?(table)
|
154
|
+
table.attributes['border'].to_s.to_i > 0
|
155
|
+
end
|
150
156
|
end
|
151
157
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: html_to_plain_text
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.0.
|
4
|
+
version: 1.0.5
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Brian Durand
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2015-
|
11
|
+
date: 2015-12-07 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: nokogiri
|