Merge branch 'master' into 0.32+configurable-self-closing-tags-take-2

* master: (23 commits) Bump ex_doc from 0.28.4 to 0.28.5 (philss#416) Bump earmark from 1.4.26 to 1.4.27 (philss#415) Bump credo from 1.6.5 to 1.6.6 (philss#414) Bump dialyxir from 1.1.0 to 1.2.0 (philss#413) Bump credo from 1.6.4 to 1.6.5 (philss#412) Show retrieval of data attributes (philss#410) Release v0.33.1 Improve the README.md file Fix warnings related to the tokenizer Change sponsors links - using GitHub Sponsors Release v0.33.0 Added case insentive variation of fl-contains (philss#409) Bump html5ever from 0.13.0 to 0.13.1 (philss#407) Bump earmark from 1.4.25 to 1.4.26 (philss#406) Minor stuff I changed while reading (philss#404) Bump earmark from 1.4.24 to 1.4.25 (philss#403) Bump html5ever from 0.12.0 to 0.13.0 (philss#401) Bump ex_doc from 0.28.3 to 0.28.4 (philss#402) Remove case of 2 for tuple of :pi (philss#400) Bump earmark from 1.4.23 to 1.4.24 (philss#398) ...
inoas · Aug 24, 2022 · 6138a92 · 6138a92
2 parents a418551 + 55d54a4
commit 6138a92
Show file tree

Hide file tree

Showing 18 changed files with 182 additions and 120 deletions.
diff --git a/.github/FUNDING.yml b/.github/FUNDING.yml
@@ -1,2 +1,2 @@
+github: philss
 ko_fi: philipsampaio
-custom: https://www.paypal.com/donate?business=EMDBKWVHVEB7Q&currency_code=USD
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -1,6 +1,10 @@
 name: CI
 
-on: [push, pull_request]
+on:
+  pull_request:
+  push:
+    branches:
+      - master
 
 jobs:
   test:
@@ -13,12 +17,12 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        elixir: ["1.12.3", "1.8.2"]
-        otp: ["24.1", "22.3"]
+        elixir: ["1.13.3", "1.10.4"]
+        otp: ["24.3.2", "22.3.4"]
         parser: [fast_html, html5ever, mochiweb]
         exclude:
-          - elixir: "1.8.2"
-            otp: "24.1"
+          - elixir: "1.10.4"
+            otp: "24.3.2"
 
     steps:
       - uses: actions/checkout@v2
@@ -44,7 +48,7 @@ jobs:
 
       - name: Check format
         run: mix format --check-formatted
-        if: matrix.elixir == '1.12.3'
+        if: matrix.elixir == '1.13.3'
 
       - name: Run test
         run: |-

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -7,6 +7,24 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 
 ## [Unreleased][unreleased]
 
+## [0.33.1] - 2022-06-28
+
+### Fixed
+
+- Remove some warnings for unused code.
+
+## [0.33.0] - 2022-06-28
+
+### Added
+
+- Add support for searching elements that contains text in a case-insensitive manner with
+`fl-icontains` - thanks [@nuno84](https://github.com/nuno84)
+
+### Changed
+
+- Drop support for Elixir 1.8 and 1.9.
+- Fix and improve internal things - thanks [@derek-zhou](https://github.com/derek-zhou) and [@hissssst](https://github.com/hissssst)
+
 ## [0.32.1] - 2022-03-24
 
 ### Fixed
@@ -596,7 +614,9 @@ of the parent element inside HTML.
 
 - Elixir version requirement from "~> 1.0.0" to ">= 1.0.0".
 
-[unreleased]: https://github.com/philss/floki/compare/v0.32.1...HEAD
+[unreleased]: https://github.com/philss/floki/compare/v0.33.1...HEAD
+[0.33.1]: https://github.com/philss/floki/compare/v0.33.0...v0.33.1
+[0.33.0]: https://github.com/philss/floki/compare/v0.32.1...v0.33.0
 [0.32.1]: https://github.com/philss/floki/compare/v0.32.0...v0.32.1
 [0.32.0]: https://github.com/philss/floki/compare/v0.31.0...v0.32.0
 [0.31.0]: https://github.com/philss/floki/compare/v0.30.1...v0.31.0

diff --git a/README.md b/README.md
@@ -9,7 +9,7 @@
 
 **Floki is a simple HTML parser that enables search for nodes using CSS selectors**.
 
-[Check the documentation](https://hexdocs.pm/floki).
+[Check the documentation 📙](https://hexdocs.pm/floki).
 
 ## Usage
 
@@ -61,7 +61,7 @@ Add Floki to your `mix.exs`:
 ```elixir
 defp deps do
   [
-    {:floki, "~> 0.32.0"}
+    {:floki, "~> 0.33.0"}
   ]
 end
 ```
@@ -112,16 +112,14 @@ Extracting the files is needed only once.
 
 #### Using `html5ever` as the HTML parser
 
-Rust needs to be installed on the system in order to compile html5ever. To do that, please
-[follow the instruction](https://www.rust-lang.org/en-US/install.html) presented in the official page.
-
-After Rust is set up, you need to add `html5ever` NIF to your dependency list:
+This dependency is written with a NIF using [Rustler](https://github.com/rusterlium/rustler), but
+you don't need to install anything to compile it thanks to [RustlerPrecompiled](https://hexdocs.pm/rustler_precompiled/).
 
 ```elixir
 defp deps do
   [
-    {:floki, "~> 0.32.0"},
-    {:html5ever, "~> 0.9.0"}
+    {:floki, "~> 0.33.0"},
+    {:html5ever, "~> 0.13.0"}
   ]
 end
 ```
@@ -136,7 +134,7 @@ Then you need to configure your app to use `html5ever`:
 config :floki, :html_parser, Floki.HTMLParser.Html5ever
 ```
 
-For more info, check the article [Rustler - Safe Erlang and Elixir NIFs in Rust](http://hansihe.com/2017/02/05/rustler-safe-erlang-elixir-nifs-in-rust.html).
+Notice that you can pass the HTML parser as an option in `parse_document/2` and `parse_fragment/2`.
 
 #### Using `fast_html` as the HTML parser
 
@@ -148,7 +146,7 @@ First, add `fast_html` to your dependencies:
 ```elixir
 defp deps do
   [
-    {:floki, "~> 0.32.0"},
+    {:floki, "~> 0.33.0"},
     {:fast_html, "~> 2.0"}
   ]
 end
@@ -259,9 +257,10 @@ Here you find all the [CSS selectors](https://www.w3.org/TR/selectors/#selectors
 
 There are also some selectors based on non-standard specifications. They are:
 
-| Pattern              | Description                                         |
-|----------------------|-----------------------------------------------------|
-| E:fl-contains('foo') | an E element that contains "foo" inside a text node |
+| Pattern               | Description                                                            |
+|-----------------------|------------------------------------------------------------------------|
+| E:fl-contains('foo')  | an E element that contains "foo" inside a text node                    |
+| E:fl-icontains('foo') | an E element that contains "foo" inside a text node (case insensitive) |
 
 ## Special thanks
 

diff --git a/config/config.exs b/config/config.exs
@@ -1,4 +1,4 @@
-use Mix.Config
+import Config
 
 config :logger, :console,
   format: "$metadata $message\n",

diff --git a/lib/floki.ex b/lib/floki.ex
@@ -570,6 +570,8 @@ defmodule Floki do
       iex> Floki.attribute([{"a", [{"class", "foo"}, {"href", "https://google.com"}], ["Google"]}], "a", "class")
       ["foo"]
 
+      iex> Floki.attribute([{"a", [{"href", "https://google.com"}, {"data-name", "google"}], ["Google"]}], "a[data-name]", "data-name")
+      ["google"]
   """
 
   @spec attribute(binary | html_tree | html_node, binary, binary) :: list
@@ -588,6 +590,8 @@ defmodule Floki do
       iex> Floki.attribute([{"a", [{"href", "https://google.com"}], ["Google"]}], "href")
       ["https://google.com"]
 
+      iex> Floki.attribute([{"a", [{"href", "https://google.com"}, {"data-name", "google"}], ["Google"]}], "data-name")
+      ["google"]
   """
 
   @spec attribute(binary | html_tree | html_node, binary) :: list

diff --git a/lib/floki/html/tokenizer.ex b/lib/floki/html/tokenizer.ex
@@ -746,36 +746,37 @@ defmodule Floki.HTML.Tokenizer do
 
   # § tokenizer-script-data-escape-start-state: re-entrant
 
-  @spec script_data_escape_start(binary(), State.t()) :: State.t()
-  def script_data_escape_start(<<?-, html::binary>>, s) do
-    script_data_escape_start_dash(
-      html,
-      %{
-        s
-        | tokens: append_char_token(s, @hyphen_minus)
-      }
-    )
-  end
-
-  def script_data_escape_start(html, s) do
-    script_data(html, s)
-  end
+  ## Unused
+  # @spec script_data_escape_start(binary(), State.t()) :: State.t()
+  # def script_data_escape_start(<<?-, html::binary>>, s) do
+  #   script_data_escape_start_dash(
+  #     html,
+  #     %{
+  #       s
+  #       | tokens: append_char_token(s, @hyphen_minus)
+  #     }
+  #   )
+  # end
+
+  # def script_data_escape_start(html, s) do
+  #   script_data(html, s)
+  # end
 
   # § tokenizer-script-data-escape-start-dash-state
 
-  defp script_data_escape_start_dash(<<?-, html::binary>>, s) do
-    script_data_escaped_dash_dash(
-      html,
-      %{
-        s
-        | tokens: append_char_token(s, @hyphen_minus)
-      }
-    )
-  end
+  # defp script_data_escape_start_dash(<<?-, html::binary>>, s) do
+  #   script_data_escaped_dash_dash(
+  #     html,
+  #     %{
+  #       s
+  #       | tokens: append_char_token(s, @hyphen_minus)
+  #     }
+  #   )
+  # end
 
-  defp script_data_escape_start_dash(html, s) do
-    script_data(html, s)
-  end
+  # defp script_data_escape_start_dash(html, s) do
+  #   script_data(html, s)
+  # end
 
   # § tokenizer-script-data-escaped-state
 
@@ -1740,15 +1741,15 @@ defmodule Floki.HTML.Tokenizer do
   end
 
   defp comment_end(html, s) do
-    new_comment = %Comment{s.token | data: [s.token.data | "--"]}
+    new_comment = %Comment{s.token | data: [s.token.data | ["--"]]}
 
     comment(html, %{s | token: new_comment})
   end
 
   # § tokenizer-comment-end-bang-state
 
   defp comment_end_bang(<<?-, html::binary>>, s) do
-    new_comment = %Comment{s.token | data: [s.token.data | "--!"]}
+    new_comment = %Comment{s.token | data: [s.token.data | ["--!"]]}
 
     comment_end_dash(html, %{s | token: new_comment})
   end
@@ -1772,7 +1773,7 @@ defmodule Floki.HTML.Tokenizer do
   end
 
   defp comment_end_bang(html, s) do
-    new_comment = %Comment{s.token | data: [s.token.data | "--!"]}
+    new_comment = %Comment{s.token | data: [s.token.data | ["--!"]]}
 
     comment(html, %{s | token: new_comment})
   end

diff --git a/lib/floki/selector.ex b/lib/floki/selector.ex
@@ -49,6 +49,9 @@ defmodule Floki.Selector do
     defp classes(%{classes: classes}), do: ".#{Enum.join(classes, ".")}"
   end
 
+  @wildcards [nil, "*"]
+  defguardp is_wildcard(x) when x in @wildcards
+
   @doc false
 
   # Returns if a given node matches with a given selector.
@@ -94,31 +97,29 @@ defmodule Floki.Selector do
     end)
   end
 
-  defp namespace_match?(_node, nil), do: true
-  defp namespace_match?(_node, "*"), do: true
+  defp namespace_match?(_node, namespace) when is_wildcard(namespace), do: true
   defp namespace_match?(%HTMLNode{type: :pi}, _type), do: false
 
   defp namespace_match?(%HTMLNode{type: type_maybe_with_namespace}, namespace) do
     case String.split(type_maybe_with_namespace, ":") do
-      [ns, _type] ->
-        ns == namespace
+      [^namespace, _type] ->
+        true
 
-      [_type] ->
+      _ ->
         false
     end
   end
 
-  defp type_match?(_node, nil), do: true
-  defp type_match?(_node, "*"), do: true
+  defp type_match?(_node, type) when is_wildcard(type), do: true
   defp type_match?(%HTMLNode{type: :pi}, _type), do: false
 
   defp type_match?(%HTMLNode{type: type_maybe_with_namespace}, type) do
     case String.split(type_maybe_with_namespace, ":") do
-      [_ns, tp] ->
-        tp == type
+      [_ns, ^type] ->
+        true
 
-      [tp] ->
-        tp == type
+      [^type] ->
+        true
 
       _ ->
         false
@@ -131,11 +132,10 @@ defmodule Floki.Selector do
   defp classes_matches?(%HTMLNode{attributes: []}, _), do: false
 
   defp classes_matches?(%HTMLNode{attributes: attributes}, classes) do
-    Enum.all?(classes, fn class ->
-      selector = %AttributeSelector{match_type: :includes, attribute: "class", value: class}
-
-      AttributeSelector.match?(attributes, selector)
-    end)
+    case :proplists.get_value("class", attributes, nil) do
+      nil -> false
+      class -> classes -- String.split(class, ~r/\s+/) == []
+    end
   end
 
   defp attributes_matches?(_node, []), do: true
@@ -210,6 +210,11 @@ defmodule Floki.Selector do
     PseudoClass.match_contains?(tree, html_node, pseudo_class)
   end
 
+  # Case insensitive contains
+  defp pseudo_class_match?(html_node, pseudo_class = %{name: "fl-icontains"}, tree) do
+    PseudoClass.match_icontains?(tree, html_node, pseudo_class)
+  end
+
   defp pseudo_class_match?(html_node, %{name: "root"}, tree) do
     PseudoClass.match_root?(html_node, tree)
   end