algolia_html_extractor 2.6.0 → 2.6.1
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/lib/algolia_html_extractor.rb +6 -1
- data/lib/version.rb +1 -1
- metadata +1 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: cf26475758c9b8aaccd120f0a9fbfec4d6446a24
|
4
|
+
data.tar.gz: 6aa13ec0687cd1949a0b1b2a7ed08b1686d50cc1
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: f10c93aa21388d46178cac6019505b0f5e374df9a4374c27bb8b401c5c1e759c9b68b732d0cd8d599d893dec5d6ab7a8eda2df4db0bb05b12e8b0811d27a47a7
|
7
|
+
data.tar.gz: db353bf1f3ee22dc75d645a68c07de2633bddb1bb20d53dd15f118e924a8aaee3bb5956aac593642741d76660ccf80e8668c8b83ca73e1db31286f55c3fd1947
|
@@ -8,7 +8,8 @@ module AlgoliaHTMLExtractor
|
|
8
8
|
def self.default_options(options)
|
9
9
|
default_options = {
|
10
10
|
css_selector: 'p',
|
11
|
-
heading_selector: 'h1,h2,h3,h4,h5,h6'
|
11
|
+
heading_selector: 'h1,h2,h3,h4,h5,h6',
|
12
|
+
tags_to_exclude: ''
|
12
13
|
}
|
13
14
|
default_options.merge(options)
|
14
15
|
end
|
@@ -22,6 +23,7 @@ module AlgoliaHTMLExtractor
|
|
22
23
|
options = default_options(options)
|
23
24
|
heading_selector = options[:heading_selector]
|
24
25
|
css_selector = options[:css_selector]
|
26
|
+
tags_to_exclude = options[:tags_to_exclude]
|
25
27
|
|
26
28
|
items = []
|
27
29
|
current_hierarchy = {
|
@@ -56,6 +58,9 @@ module AlgoliaHTMLExtractor
|
|
56
58
|
# Stop if node is not to be extracted
|
57
59
|
next unless node.matches?(css_selector)
|
58
60
|
|
61
|
+
# Removing excluded child from the node
|
62
|
+
node.search(tags_to_exclude).each(&:remove) unless tags_to_exclude.empty?
|
63
|
+
|
59
64
|
# Stop if node is empty
|
60
65
|
content = extract_text(node)
|
61
66
|
next if content.empty?
|
data/lib/version.rb
CHANGED