curation 2.0.1 → 2.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c2062c7ec7fb444d27f102d26658b386a01a964ea4e03aa0d81a472316012d11
-  data.tar.gz: 634f5216e61801b3ac42c8b340d5012c101024f4d5b5e0ba155c01a89f38cafb
+  metadata.gz: f4c4661f04dfa6c3442537bf91ded409452311936ec3e2dedce8fa48ac6ba5d1
+  data.tar.gz: d48f91295be205e59d3028907f1f6dfa9e0d83bc5322834b4b8b21ce824e62a2
 SHA512:
-  metadata.gz: 15008b92c6a51fdf9bd79b9f1da01d59323c13589b6e8ccd5d8754b96153173fe8a2cdffa5faa45a4d38c92b097a35012f8dff98fea6244ade8c9af22c13d1cc
-  data.tar.gz: 96a29d3c8482fce0101f91a3f24eafaec51a9115f2169831b67939edf79a47d7f5bb0c3223466de355cf8a367143a262cc54a1d5e4dd7e6bffe2d310879a9cae
+  metadata.gz: dbcc3db9b67f0b91773a1e72626d17c9e3ded02054f6b348bc5264005c09518d568e851f080e780316e32455941ee92146daa35c61c6fc3866806d698a949672
+  data.tar.gz: 0c03a44f6f97cf5f0180db1832989c9e0eadd0e7250d3f44a5c4cd6a10d9f42d437081a53449fe40a2c63b4e4b398eedc763fd29f7e3173bab3ee10fd7ca157a

data/Gemfile

@@ -7,3 +7,4 @@ gem 'rake', '~> 12.0'
 gem 'minitest'
 gem 'minitest-reporters'
 gem 'byebug'
+

data/Gemfile.lock

@@ -1,10 +1,11 @@
 PATH
   remote: .
   specs:
-    curation (2.0.1)
+    curation (2.0.2)
       htmlentities
       metainspector
       nokogiri
+      rails-html-sanitizer
 
 GEM
   remote: https://rubygems.org/
@@ -15,6 +16,7 @@ GEM
     base64 (0.2.0)
     builder (3.2.4)
     byebug (11.1.3)
+    crass (1.0.6)
     domain_name (0.5.20190701)
       unf (>= 0.0.5, < 1.0.0)
     faraday (2.7.11)
@@ -40,6 +42,9 @@ GEM
     htmlentities (4.3.4)
     http-cookie (1.0.5)
       domain_name (~> 0.5)
+    loofah (2.21.4)
+      crass (~> 1.0.2)
+      nokogiri (>= 1.12.0)
     metainspector (5.15.0)
       addressable (~> 2.8.4)
       faraday (~> 2.5)
@@ -63,6 +68,9 @@ GEM
       racc (~> 1.4)
     public_suffix (5.0.3)
     racc (1.7.3)
+    rails-html-sanitizer (1.6.0)
+      loofah (~> 2.21)
+      nokogiri (~> 1.14)
     rake (12.3.3)
     ruby-progressbar (1.13.0)
     ruby2_keywords (0.0.5)

data/curation.gemspec

@@ -24,4 +24,5 @@ Gem::Specification.new do |spec|
   spec.add_dependency "metainspector"
   spec.add_dependency "nokogiri"
   spec.add_dependency "htmlentities"
+  spec.add_dependency "rails-html-sanitizer"
 end

data/lib/curation/finders/text.rb

@@ -26,8 +26,8 @@ module Text
     text = text.gsub('<br><br>', '<br>')
     text = text.gsub(/\s+/, ' ')
     text = clean_encoding(text)
+    text = Rails::HTML5::FullSanitizer.new.sanitize(text)
     text
-
   end
 
   def find_text

data/lib/curation/version.rb

@@ -1,3 +1,3 @@
 module Curation
-  VERSION = "2.0.1"
+  VERSION = "2.0.2"
 end

data/lib/curation.rb

@@ -10,6 +10,7 @@ require "curation/finders/title"
 require "metainspector"
 require "open-uri"
 require "htmlentities"
+require "rails-html-sanitizer"
 
 module Curation
   class Error < StandardError; end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: curation
 version: !ruby/object:Gem::Version
-  version: 2.0.1
+  version: 2.0.2
 platform: ruby
 authors:
 - Arnaud Levy
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2023-11-11 00:00:00.000000000 Z
+date: 2023-11-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: metainspector
@@ -52,6 +52,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: rails-html-sanitizer
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 description: When you build content curation tools, you need to extract the content
   of pages (title, text, image...). This requires different strategies and some fine
   tuning to work efficiently.