loofah 2.13.0 → 2.14.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 1d9193264008cab1a3f6b35a5b0c6862e781f99385a35d3f6c6714930bd18d3c
-  data.tar.gz: 0b8651064006fb2b5ac201b11e24e0bebc8ec4ab523a3b3d830514247d498e28
+  metadata.gz: 95836cdfac672774704d62557836c319edf8c1ffd17323b61c749aabbb71f6b6
+  data.tar.gz: ddc0bc8f3dc588cc4a69651debacb404cedc02e047f585bde0758ec4186d6018
 SHA512:
-  metadata.gz: a7929ae8c091cbf9930e9b8f0f5a16dbf3b02e9f3ab9606370dd205c1153a72b921e9d7878c96be2ad7b968273f6ebb1d297eb984fefa0ac8367140835f0a50d
-  data.tar.gz: d946f74bc710c3018f790a670290d94cc1d75d494a899d9116336a76a52e3f30ab1ba1122e18b45d22766c0e2c86a3b17c2ca0ab8dcdacf03323a80cfc493b46
+  metadata.gz: 05b043ea1e8de851488dc084cae3f596816b54549cfc4f9a1d5fd675093d8dc06956e6880286adcdcffe5aca6d29e46a97052cc526cc7b3667277ff8a9575ba7
+  data.tar.gz: fd0fbee37a8150709ba178889d96532a4b2efdd402ccc2d922c2022a88f04188ebc221037d522cf7af67eaf3f1c4d74acba1de37ca2f70e1d0214afff69f6f85

data/CHANGELOG.md

@@ -1,5 +1,12 @@
 # Changelog
 
+## 2.14.0 / 2022-02-11
+
+### Features
+
+* The `#to_text` method on `Loofah::HTML::{Document,DocumentFragment}` replaces `<br>` line break elements with a newline. [[#225](https://github.com/flavorjones/loofah/issues/225)]
+
+
 ## 2.13.0 / 2021-12-10
 
 ### Bug fixes

data/README.md

@@ -133,13 +133,12 @@ and `text` to return plain text:
 doc.text    # => "ohai! div is safe "
 ```
 
-Also, `to_text` is available, which does the right thing with
-whitespace around block-level elements.
+Also, `to_text` is available, which does the right thing with whitespace around block-level and line break elements.
 
 ``` ruby
-doc = Loofah.fragment("<h1>Title</h1><div>Content</div>")
-doc.text    # => "TitleContent"           # probably not what you want
-doc.to_text # => "\nTitle\n\nContent\n"   # better
+doc = Loofah.fragment("<h1>Title</h1><div>Content<br>Next line</div>")
+doc.text    # => "TitleContentNext line"            # probably not what you want
+doc.to_text # => "\nTitle\n\nContent\nNext line\n"  # better
 ```
 
 ### Loofah::XML::Document and Loofah::XML::DocumentFragment

data/lib/loofah/elements.rb

@@ -70,8 +70,6 @@ module Loofah
                                          video
                                        ]
 
-    STRICT_BLOCK_LEVEL = STRICT_BLOCK_LEVEL_HTML4 + STRICT_BLOCK_LEVEL_HTML5
-
     # The following elements may also be considered block-level
     # elements since they may contain block-level elements
     LOOSE_BLOCK_LEVEL = Set.new %w[dd
@@ -86,7 +84,12 @@ module Loofah
                                    tr
                                 ]
 
+    # Elements that aren't block but should generate a newline in #to_text
+    INLINE_LINE_BREAK = Set.new(["br"])
+
+    STRICT_BLOCK_LEVEL = STRICT_BLOCK_LEVEL_HTML4 + STRICT_BLOCK_LEVEL_HTML5
     BLOCK_LEVEL = STRICT_BLOCK_LEVEL + LOOSE_BLOCK_LEVEL
+    LINEBREAKERS = BLOCK_LEVEL + INLINE_LINE_BREAK
   end
 
   ::Loofah::MetaHelpers.add_downcased_set_members_to_all_set_constants ::Loofah::Elements

data/lib/loofah/instance_methods.rb

@@ -112,11 +112,11 @@ module Loofah
     #  Returns a plain-text version of the markup contained by the
     #  fragment, with HTML entities encoded.
     #
-    #  This method is slower than #to_text, but is clever about
-    #  whitespace around block elements.
+    #  This method is slower than #text, but is clever about
+    #  whitespace around block elements and line break elements.
     #
-    #    Loofah.document("<h1>Title</h1><div>Content</div>").to_text
-    #    # => "\nTitle\n\nContent\n"
+    #    Loofah.document("<h1>Title</h1><div>Content<br>Next line</div>").to_text
+    #    # => "\nTitle\n\nContent\nNext line\n"
     #
     def to_text(options = {})
       Loofah.remove_extraneous_whitespace self.dup.scrub!(:newline_block_elements).text(options)

data/lib/loofah/scrubbers.rb

@@ -240,8 +240,13 @@ module Loofah
       end
 
       def scrub(node)
-        return CONTINUE unless Loofah::Elements::BLOCK_LEVEL.include?(node.name)
-        node.add_next_sibling Nokogiri::XML::Text.new("\n#{node.content}\n", node.document)
+        return CONTINUE unless Loofah::Elements::LINEBREAKERS.include?(node.name)
+        replacement = if Loofah::Elements::INLINE_LINE_BREAK.include?(node.name)
+          "\n"
+        else
+          "\n#{node.content}\n"
+        end
+        node.add_next_sibling Nokogiri::XML::Text.new(replacement, node.document)
         node.remove
       end
     end

data/lib/loofah/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 module Loofah
   # The version of Loofah you are using
-  VERSION = "2.13.0"
+  VERSION = "2.14.0"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: loofah
 version: !ruby/object:Gem::Version
-  version: 2.13.0
+  version: 2.14.0
 platform: ruby
 authors:
 - Mike Dalessio
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2021-12-10 00:00:00.000000000 Z
+date: 2022-02-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: crass
@@ -199,7 +199,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.32
+rubygems_version: 3.3.5
 signing_key: 
 specification_version: 4
 summary: Loofah is a general library for manipulating and transforming HTML/XML documents