selma 0.2.2-x64-mingw-ucrt → 0.3.0-x64-mingw-ucrt

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: cddfc47a2aa3a984e53589ef144ed42def29c873b8d23ab49332029ec3fef636
-  data.tar.gz: 232e4467a26c4e2fe925dc7925988c3124634e707679c2ca6238c6c3f1c10628
+  metadata.gz: a0ddf7d69640ad327cf8e8efd8e35e0441f6d4910e98d98629f96254d22268f8
+  data.tar.gz: 0c1ff8f5237f35d2353b6d78f79a2316ae052631094920cb17ff8dda5062ff56
 SHA512:
-  metadata.gz: 1fbfaf72050162e33ec809997564b7f3b93de1c069afea1fa9472769f624fad63b546043a3481f00eec58eb82001d84d2a4f3846586ae7b2fabbb5148269e420
-  data.tar.gz: 234a57063302225e67220cab81eabb0dd5e3b60b82cb1418184bddfbac39eb6e9b4cd9a358f75abdd528eb523bef608fd4f50f53f4a791e7e98867808cc7e3c6
+  metadata.gz: 94ecfa9b7f1ef2f36a9397880ed901900fc128996d3c79b4ef337cbd7f3e0fbeebcd66dea3e509b29cffb2a21a951f49263648c8485a4954d7ccd5987f532e52
+  data.tar.gz: 806f0ed6ff134d58e7aa5a63a455ee5e0364a29d77b2169893d1712c9268b43efd5f1f1c1dcb8c98b2092efdd0133846043868680d69b30a55847051ec9b3365

data/README.md

@@ -76,7 +76,7 @@ attributes: {
 
 # URL handling protocols to allow in specific attributes. By default, no
 # protocols are allowed. Use :relative in place of a protocol if you want
-# to allow relative URLs sans protocol.
+# to allow relative URLs sans protocol. Set to `:all` to allow any protocol.
 protocols: {
     "a" => { "href" => ["http", "https", "mailto", :relative] },
     "img" => { "href" => ["http", "https"] },
@@ -103,7 +103,11 @@ Here's an example which rewrites the `href` attribute on `a` and the `src` attri
 
 ```ruby
 class MatchAttribute
-  SELECTOR = Selma::Selector(match_element: %(a[href^="http:"], img[src^="http:"]"))
+  SELECTOR = Selma::Selector.new(match_element: %(a[href^="http:"], img[src^="http:"]"))
+
+  def selector
+    SELECTOR
+  end
 
   def handle_element(element)
     if element.tag_name == "a"
@@ -178,38 +182,118 @@ The `element` argument in `handle_element` has the following methods:
 
 ## Benchmarks
 
+When `bundle exec rake benchmark`, two different benchmarks are calculated. Here are those results on my machine.
+
+### Benchmarks for just the sanitization process
+
+Comparing Selma against popular Ruby sanitization gems:
+
+<!-- prettier-ignore-start -->
 <details>
 <pre>
-ruby test/benchmark.rb
-ruby test/benchmark.rb
 Warming up --------------------------------------
-sanitize-document-huge
-                         1.000  i/100ms
- selma-document-huge     1.000  i/100ms
+         sanitize-sm    15.000 i/100ms
+            selma-sm   126.000 i/100ms
+Calculating -------------------------------------
+         sanitize-sm    155.074 (± 1.9%) i/s -      4.665k in  30.092214s
+            selma-sm      1.290k (± 1.3%) i/s -     38.808k in  30.085333s
+
+Comparison:
+            selma-sm:     1290.1 i/s
+         sanitize-sm:      155.1 i/s - 8.32x  slower
+
+input size = 86686 bytes, 0.09 MB
+
+ruby 3.3.0 (2023-12-25 revision 5124f9ac75) [arm64-darwin23]
+Warming up --------------------------------------
+         sanitize-md     3.000 i/100ms
+            selma-md    33.000 i/100ms
 Calculating -------------------------------------
-sanitize-document-huge
-                          0.257  (± 0.0%) i/s -      2.000  in   7.783398s
- selma-document-huge      4.602  (± 0.0%) i/s -     23.000  in   5.002870s
+         sanitize-md     40.321 (± 5.0%) i/s -      1.206k in  30.004711s
+            selma-md    337.417 (± 1.5%) i/s -     10.131k in  30.032772s
+
+Comparison:
+            selma-md:      337.4 i/s
+         sanitize-md:       40.3 i/s - 8.37x  slower
+
+input size = 7172510 bytes, 7.17 MB
+
+ruby 3.3.0 (2023-12-25 revision 5124f9ac75) [arm64-darwin23]
 Warming up --------------------------------------
-sanitize-document-medium
-                         2.000  i/100ms
-selma-document-medium
-                        22.000  i/100ms
+         sanitize-lg     1.000 i/100ms
+            selma-lg     1.000 i/100ms
 Calculating -------------------------------------
-sanitize-document-medium
-                         28.676  (± 3.5%) i/s -    144.000  in   5.024669s
-selma-document-medium
-                        121.500  (±22.2%) i/s -    594.000  in   5.135410s
+         sanitize-lg      0.144 (± 0.0%) i/s -      5.000 in  34.772526s
+            selma-lg      4.026 (± 0.0%) i/s -    121.000 in  30.067415s
+
+Comparison:
+            selma-lg:        4.0 i/s
+         sanitize-lg:        0.1 i/s - 27.99x  slower
+</pre>
+</details>
+<!-- prettier-ignore-end -->
+
+### Benchmarks for just the rewriting process
+
+Comparing Selma against popular Ruby HTML parsing gems:
+
+<!-- prettier-ignore-start -->
+<details>
+<pre>
+
+input size = 25309 bytes, 0.03 MB
+
+ruby 3.3.0 (2023-12-25 revision 5124f9ac75) [arm64-darwin23]
+Warming up --------------------------------------
+         nokogiri-sm    79.000 i/100ms
+       nokolexbor-sm   285.000 i/100ms
+            selma-sm   244.000 i/100ms
+Calculating -------------------------------------
+         nokogiri-sm    807.790 (± 3.1%) i/s -     24.253k in  30.056301s
+       nokolexbor-sm      2.880k (± 6.4%) i/s -     86.070k in  30.044766s
+            selma-sm      2.508k (± 1.2%) i/s -     75.396k in  30.068792s
+
+Comparison:
+       nokolexbor-sm:     2880.3 i/s
+            selma-sm:     2507.8 i/s - 1.15x  slower
+         nokogiri-sm:      807.8 i/s - 3.57x  slower
+
+input size = 86686 bytes, 0.09 MB
+
+ruby 3.3.0 (2023-12-25 revision 5124f9ac75) [arm64-darwin23]
+Warming up --------------------------------------
+         nokogiri-md     8.000 i/100ms
+       nokolexbor-md    43.000 i/100ms
+            selma-md    39.000 i/100ms
+Calculating -------------------------------------
+         nokogiri-md     87.367 (± 3.4%) i/s -      2.624k in  30.061642s
+       nokolexbor-md    438.782 (± 3.9%) i/s -     13.158k in  30.031163s
+            selma-md    392.591 (± 3.1%) i/s -     11.778k in  30.031391s
+
+Comparison:
+       nokolexbor-md:      438.8 i/s
+            selma-md:      392.6 i/s - 1.12x  slower
+         nokogiri-md:       87.4 i/s - 5.02x  slower
+
+input size = 7172510 bytes, 7.17 MB
+
+ruby 3.3.0 (2023-12-25 revision 5124f9ac75) [arm64-darwin23]
 Warming up --------------------------------------
-sanitize-document-small
-                        10.000  i/100ms
-selma-document-small    20.000  i/100ms
+         nokogiri-lg     1.000 i/100ms
+       nokolexbor-lg     1.000 i/100ms
+            selma-lg     1.000 i/100ms
 Calculating -------------------------------------
-sanitize-document-small
-                        107.280  (± 0.9%) i/s -    540.000  in   5.033850s
-selma-document-small    118.867  (±31.1%) i/s -    540.000  in   5.080726s
+         nokogiri-lg      0.895 (± 0.0%) i/s -     27.000 in  30.300832s
+       nokolexbor-lg      2.163 (± 0.0%) i/s -     65.000 in  30.085656s
+            selma-lg      5.867 (± 0.0%) i/s -    176.000 in  30.006240s
+
+Comparison:
+            selma-lg:        5.9 i/s
+       nokolexbor-lg:        2.2 i/s - 2.71x  slower
+         nokogiri-lg:        0.9 i/s - 6.55x  slower
 </pre>
 </details>
+<!-- prettier-ignore-end -->
 
 ## Contributing
 

data/lib/selma/sanitizer/config/default.rb

@@ -28,7 +28,7 @@ module Selma
 
         # URL handling protocols to allow in specific attributes. By default, no
         # protocols are allowed. Use :relative in place of a protocol if you want
-        # to allow relative URLs sans protocol.
+        # to allow relative URLs sans protocol. Set to `:all` to allow any protocol.
         protocols: {},
 
         # An Array of element names whose contents will be removed. The contents

data/lib/selma/sanitizer/config/relaxed.rb

@@ -16,6 +16,7 @@ module Selma
           "colgroup",
           "data",
           "del",
+          "details",
           "div",
           "figcaption",
           "figure",

data/lib/selma/sanitizer.rb

@@ -66,7 +66,12 @@ module Selma
     end
 
     def allow_protocol(element, attr, protos)
-      protos = [protos] unless protos.is_a?(Array)
+      if protos.is_a?(Array)
+        raise ArgumentError, "`:all` must be passed outside of an array" if protos.include?(:all)
+      else
+        protos = [protos]
+      end
+
       set_allowed_protocols(element, attr, protos)
     end
 

data/lib/selma/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Selma
-  VERSION = "0.2.2"
+  VERSION = "0.3.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: selma
 version: !ruby/object:Gem::Version
-  version: 0.2.2
+  version: 0.3.0
 platform: x64-mingw-ucrt
 authors:
 - Garen J. Torikian
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2024-01-03 00:00:00.000000000 Z
+date: 2024-06-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake