selma 0.2.2 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 50b438a2bdc8e13515ccc76c7e57a6fffb492c3ac7ff62781226ca5288f22913
-  data.tar.gz: 66b31905df161bf62a2dd88df9a5ead5e9f0a0f3a2d1464b669634dc966bc9a3
+  metadata.gz: 69919cfb80c694b6f77e4e29e29c66d7b482d96ec83a9f47d3a3711d0b636924
+  data.tar.gz: 66f9f62677e3f25391180eb9e952852a351cae1d165b2427fe9c537f05884121
 SHA512:
-  metadata.gz: f37389220da9e5b2ea7193cf1a3b7fa0198351233d5afa871c66679b06f274b161caab8b13222996345008899a5334a37150708533f3fd295ca266a5d1e35d1f
-  data.tar.gz: 2dc168d6bf3d1032fd97dd21f126bfb1028a9b62693b7bc4af254953510f259e96aa7d4c541b23a9a0160c9f5c616b40eebec05b873f0df6fc3d03dc0114f018
+  metadata.gz: fb26ee26a928c9aa30c6f71e78914317213552c21729c6ffb46712859eac21b4ddc67709584e4af9ac2a0e4e5b98acce5e5fdbdfd921afdd124faac647b0db05
+  data.tar.gz: 9ed49314dc03d3d8f7c6a3b67da8e77536a13a8efd04a8d519796751832527339d291722ac7cb3e44dab9224c2294e70378e0c37d79c97aa3f924506567a990d

data/Cargo.lock

@@ -165,18 +165,18 @@ checksum = "b5320ae4c3782150d900b79807611a59a99fc9a1d61d686faafc24b93fc8d7ca"
 
 [[package]]
 name = "enum-iterator"
-version = "1.4.1"
+version = "2.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7add3873b5dd076766ee79c8e406ad1a472c385476b9e38849f8eec24f1be689"
+checksum = "c280b9e6b3ae19e152d8e31cf47f18389781e119d4013a2a2bb0180e5facc635"
 dependencies = [
  "enum-iterator-derive",
 ]
 
 [[package]]
 name = "enum-iterator-derive"
-version = "1.2.1"
+version = "1.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "eecf8589574ce9b895052fa12d69af7a233f99e6107f5cb8dd1044f2a17bfdcb"
+checksum = "a1ab991c1362ac86c61ab6f556cff143daa22e5a15e4e189df818b2fd19fe65b"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -269,9 +269,9 @@ checksum = "b5e6163cb8c49088c2c36f57875e58ccd8c87c7427f7fbd50ea6710b2f3f2e8f"
 
 [[package]]
 name = "lol_html"
-version = "1.2.0"
+version = "1.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "10662f7aad081ec900fd735be33076da75e0389400277dc3734e2b0aa02bb115"
+checksum = "a4629ff9c2deeb7aad9b2d0f379fc41937a02f3b739f007732c46af40339dee5"
 dependencies = [
  "bitflags 2.4.1",
  "cfg-if",
@@ -282,16 +282,15 @@ dependencies = [
  "lazycell",
  "memchr",
  "mime",
- "safemem",
  "selectors",
  "thiserror",
 ]
 
 [[package]]
 name = "magnus"
-version = "0.6.2"
+version = "0.6.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4778544796676e8428e9c622460ebf284bea52d8b10db3aeb449d8b5e61b3a13"
+checksum = "b1597ef40aa8c36be098249e82c9a20cf7199278ac1c1a1a995eeead6a184479"
 dependencies = [
  "magnus-macros",
  "rb-sys",
@@ -577,12 +576,6 @@ dependencies = [
  "semver",
 ]
 
-[[package]]
-name = "safemem"
-version = "0.3.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ef703b7cb59335eae2eb93ceb664c0eb7ea6bf567079d843e09420219668e072"
-
 [[package]]
 name = "selectors"
 version = "0.22.0"

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/ext/selma/Cargo.toml

@@ -6,7 +6,7 @@ rust-version = "1.75.0"
 publish = false
 
 [dependencies]
-enum-iterator = "1.4"
+enum-iterator = "2.1"
 escapist = "0.0.2"
 magnus = "0.6"
 lol_html = "1.2"

data/ext/selma/src/sanitizer.rs

@@ -211,20 +211,23 @@ impl SelmaSanitizer {
                     }
                     Some(protocol_list) => protocol_list.push(allowed_protocol.to_string()),
                 }
-            } else if allowed_protocol.is_kind_of(class::symbol())
-                && allowed_protocol.inspect() == ":relative"
-            {
-                match protocol_list {
-                    None => {
-                        protocol_sanitizers.insert(
-                            attr_name.to_string(),
-                            vec!["#".to_string(), "/".to_string()],
-                        );
-                    }
-                    Some(protocol_list) => {
-                        protocol_list.push("#".to_string());
-                        protocol_list.push("/".to_string());
+            } else if allowed_protocol.is_kind_of(class::symbol()) {
+                let protocol_config = allowed_protocol.inspect();
+                if protocol_config == ":relative" {
+                    match protocol_list {
+                        None => {
+                            protocol_sanitizers.insert(
+                                attr_name.to_string(),
+                                vec!["#".to_string(), "/".to_string()],
+                            );
+                        }
+                        Some(protocol_list) => {
+                            protocol_list.push("#".to_string());
+                            protocol_list.push("/".to_string());
+                        }
                     }
+                } else if protocol_config == ":all" {
+                    protocol_sanitizers.insert(attr_name.to_string(), vec!["all".to_string()]);
                 }
             }
         }
@@ -388,6 +391,10 @@ impl SelmaSanitizer {
     }
 
     fn has_allowed_protocol(protocols_allowed: &[String], attr_val: &String) -> bool {
+        if protocols_allowed.contains(&"all".to_string()) {
+            return true;
+        }
+
         // FIXME: is there a more idiomatic way to do this?
         let mut pos: usize = 0;
         let mut chars = attr_val.chars();

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: ruby
 authors:
 - Garen J. Torikian
-autorequire:
+autorequire: 
 bindir: exe
 cert_chain: []
-date: 2024-01-11 00:00:00.000000000 Z
+date: 2024-06-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rb_sys
@@ -52,7 +52,7 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.2'
-description:
+description: 
 email:
 - gjtorikian@gmail.com
 executables: []
@@ -88,7 +88,7 @@ files:
 - lib/selma/sanitizer/config/restricted.rb
 - lib/selma/selector.rb
 - lib/selma/version.rb
-homepage:
+homepage: 
 licenses:
 - MIT
 metadata:
@@ -96,7 +96,7 @@ metadata:
   funding_uri: https://github.com/sponsors/gjtorikian/
   source_code_uri: https://github.com/gjtorikian/selma
   rubygems_mfa_required: 'true'
-post_install_message:
+post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
@@ -112,7 +112,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: 3.3.22
 requirements: []
 rubygems_version: 3.5.3
-signing_key:
+signing_key: 
 specification_version: 4
 summary: Selma selects and matches HTML nodes using CSS rules. Backed by Rust's lol_html
   parser.