trenni-sanitize 0.1.0 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 6fcc82f737fa654994e5e196347156bb38bfa74c
-  data.tar.gz: 7b8bafec2a1731ecc20c9f850e9620e9941a6f9d
+  metadata.gz: fd1bd015d1fe0b61494d1289eb43e200e1610e5a
+  data.tar.gz: 4ae3952d6ef7bf38a8b16ae3aff29f0a1f38dee4
 SHA512:
-  metadata.gz: 106aab6ca77fed6efc2f7f77ab5f83d5606f20fafd0b80dd05d1aa2421b5626129d02a2513b8636eb8745d3b49bf2b6c4657a60156be90193bc20faebeaa5997
-  data.tar.gz: 48735a28e214041eba2e7f1087b2c553efe7d3816ece68ae9b00dfbc970abbd06fcd34e5ee4478d8a9133f0c851b40f7f66aaa3734935daaf91237e3aaf2029e
+  metadata.gz: 7e352c69337f48b62c5292970cbb849563d4e10974a0547d9abcdc79979cc80e26523db4453c5e9c26d085b628b57a883ca86b6bbbdf05cea27f861db53b888e
+  data.tar.gz: 77aa0739c366265b9cf2fa91c256155d709f59c179fa18cac859cf26d5bcfcf5fcd61fc61c7286ce098e67c812962be39da860815f09b1ab1713b2af33377d1f

data/README.md

@@ -17,15 +17,15 @@ I use the [sanitize] gem and generally it's great. However, it's performance can
 In my informal testing, this gem is about ~50x faster than the [sanitize] gem when generating plain text.
 
 Warming up --------------------------------------
-            Sanitize    96.000  i/100ms
-    Trenni::Sanitize     4.447k i/100ms
+						Sanitize    96.000  i/100ms
+		Trenni::Sanitize     4.447k i/100ms
 Calculating -------------------------------------
-            Sanitize    958.020  (± 4.5%) i/s -      4.800k in   5.020564s
-    Trenni::Sanitize     44.718k (± 4.2%) i/s -    226.797k in   5.080756s
+						Sanitize    958.020  (± 4.5%) i/s -      4.800k in   5.020564s
+		Trenni::Sanitize     44.718k (± 4.2%) i/s -    226.797k in   5.080756s
 
 Comparison:
-    Trenni::Sanitize:    44718.1 i/s
-            Sanitize:      958.0 i/s - 46.68x  slower
+		Trenni::Sanitize:    44718.1 i/s
+						Sanitize:      958.0 i/s - 46.68x  slower
 
 ## Installation
 
@@ -51,9 +51,8 @@ You can extract text using something similar to the following parser delegate:
 
 ```ruby
 class Text < Trenni::Sanitize::Filter
-	def filter(tag)
-		# Filter out all tags
-		return false
+	def filter(node)
+		skip!(TAG)
 	end
 	
 	def doctype(string)
@@ -61,11 +60,6 @@ class Text < Trenni::Sanitize::Filter
 	
 	def instruction(string)
 	end
-	
-	def text(string)
-		# Output all text
-		@output << string
-	end
 end
 
 text = Text.parse("<p>Hello World</p>").output
@@ -88,11 +82,12 @@ class Fragment < Trenni::Sanitize::Filter
 		'a' => ['href', 'target']
 	}.freeze
 	
-	def filter(tag)
-		if attributes = ALLOWED_TAGS[tag.name]
-			tag.attributes.slice!(attributes)
-			
-			return tag
+	def filter(node)
+		if attributes = ALLOWED_TAGS[node.name]
+			node.tag.attributes.slice!(attributes)
+		else
+			# Skip the tag, and all contents
+			skip!(ALL)
 		end
 	end
 	

data/lib/trenni/sanitize/filter.rb

@@ -59,6 +59,10 @@ module Trenni
 					(self.skip & mode) == mode
 				end
 				
+				def accept!(mode = ALL)
+					self.skip &= ~mode
+				end
+				
 				def [] key
 					self.tag.attributes[key]
 				end
@@ -82,18 +86,29 @@ module Trenni
 			# The current node being parsed.
 			attr :current
 			
+			attr :stack
+			
 			def top
 				@stack.last || @top
 			end
 			
 			def parse!(input)
+				parse_begin
+				
 				Trenni::Parsers.parse_markup(input, self, @entities)
 				
+				parse_end
+				
+				return self
+			end
+			
+			def parse_begin
+			end
+			
+			def parse_end
 				while @stack.size > 1
 					close_tag(@stack.last.name)
 				end
-				
-				return self
 			end
 			
 			def open_tag_begin(name, offset)

data/lib/trenni/sanitize/fragment.rb

@@ -49,7 +49,9 @@ module Trenni
 			
 			def filter(node)
 				if attributes = ALLOWED_TAGS[node.name]
-					node.tag.attributes.slice!(attributes)
+					node.tag.attributes.slice!(*attributes)
+					
+					node.accept!
 				else
 					node.skip!
 				end

data/lib/trenni/sanitize/version.rb

@@ -20,6 +20,6 @@
 
 module Trenni
 	module Sanitize
-		VERSION = "0.1.0"
+		VERSION = "0.2.0"
 	end
 end

data/spec/trenni/sanitize/extensions_spec.rb

@@ -0,0 +1,26 @@
+
+require 'trenni/sanitize/extensions'
+
+RSpec.describe Hash do
+	let(:hash) {{x: 10, y: 20, z: 30}}
+	
+	it "can slice the hash" do
+		result = hash.slice(:x)
+		
+		expect(hash.size).to be == 3
+		expect(result.size).to be == 1
+		
+		expect(result[:x]).to be == 10
+		expect(result[:y]).to be_nil
+		expect(result[:z]).to be_nil
+	end
+	
+	it "can slice! the hash in-place" do
+		hash.slice!(:x)
+		
+		expect(hash.size).to be == 1
+		expect(hash[:x]).to be == 10
+		expect(hash[:y]).to be_nil
+		expect(hash[:z]).to be_nil
+	end
+end

data/spec/trenni/sanitize/fragment_spec.rb

@@ -56,5 +56,11 @@ RSpec.describe Trenni::Sanitize::Fragment do
 		
 		expect(fragment.output).to be == "x&y"
 	end
+	
+	it "should include nested img" do
+		fragment = described_class.parse("<table><img src='foo'/></table>")
+		
+		expect(fragment.output).to be == "<img src=\"foo\"/>"
+	end
 end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: trenni-sanitize
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors:
 - Samuel Williams
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-02-14 00:00:00.000000000 Z
+date: 2018-02-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: trenni
@@ -88,6 +88,7 @@ files:
 - lib/trenni/sanitize/version.rb
 - spec/spec_helper.rb
 - spec/trenni/sanitize/benchmark_spec.rb
+- spec/trenni/sanitize/extensions_spec.rb
 - spec/trenni/sanitize/fragment_spec.rb
 - spec/trenni/sanitize/sample.html
 - spec/trenni/sanitize/text_spec.rb
@@ -118,6 +119,7 @@ summary: Sanitize markdown according to a set of rules.
 test_files:
 - spec/spec_helper.rb
 - spec/trenni/sanitize/benchmark_spec.rb
+- spec/trenni/sanitize/extensions_spec.rb
 - spec/trenni/sanitize/fragment_spec.rb
 - spec/trenni/sanitize/sample.html
 - spec/trenni/sanitize/text_spec.rb