Packages

floki

0.36.2
0.38.4 0.38.3 0.38.2 0.38.1 0.38.0 0.37.1 0.37.0 0.36.3 0.36.2 0.36.1 0.36.0 0.35.4 0.35.3 0.35.2 0.35.1 0.35.0 0.34.3 0.34.2 0.34.1 0.34.0 0.33.1 0.33.0 0.32.1 0.32.0 0.31.0 0.30.1 0.30.0 0.29.0 0.28.0 0.27.0 0.26.0 0.25.0 0.24.0 0.23.1 0.23.0 0.22.0 0.21.0 0.20.4 0.20.3 0.20.2 0.20.1 0.20.0 0.19.3 0.19.2 0.19.1 0.19.0 0.18.1 0.18.0 0.17.2 0.17.1 0.17.0 0.16.0 0.15.0 0.14.0 0.13.2 0.13.1 0.13.0 0.12.1 0.12.0 0.11.0 0.10.1 0.10.0 0.9.0 0.8.1 0.8.0 0.7.2 0.7.1 0.7.0 0.6.1 0.6.0 0.5.0 0.4.1 0.4.0 0.3.3 0.3.2 0.3.1 0.3.0 0.2.1 0.2.0 0.1.1 0.1.0 0.0.5 0.0.4 0.0.3 0.0.2 0.0.1

Floki is a simple HTML parser that enables search for nodes using CSS selectors.

HexDocs

Current section

86 Versions

Jump to
Readme
86 Versions
0 Dependencies
Dependants
Files
Activity
Hide whitespace

Compare versions

5 files changed
+127 additions
-42 deletions
  @@ -7,6 +7,22 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
7 7
8 8 ## [Unreleased][unreleased]
9 9
10 + ## [0.36.2] - 2024-04-26
11 +
12 + ### Added
13 +
14 + - Implement the `Inspect` protocol for the `Floki.HTMLTree` struct.
15 + This struct is currently private. Thank you [@vittoriabitton](https://github.com/vittoriabitton).
16 +
17 + ### Fixed
18 +
19 + - Fix regression to respect config option `:encode` in `Floki.raw_html/2`.
20 + Thanks [@Sgoettschkes](https://github.com/Sgoettschkes).
21 +
22 + - Make the `Floki.raw_html/2` treat the contents of the `<title>` tag as plain text.
23 + The idea is to align with `parse_document/2`.
24 + Thank you [@aymanosman](https://github.com/aymanosman).
25 +
10 26 ## [0.36.1] - 2024-03-18
11 27
12 28 ### Fixed
  @@ -770,7 +786,8 @@ of the parent element inside HTML.
770 786
771 787 - Elixir version requirement from "~> 1.0.0" to ">= 1.0.0".
772 788
773 - [unreleased]: https://github.com/philss/floki/compare/v0.36.1...HEAD
789 + [unreleased]: https://github.com/philss/floki/compare/v0.36.2...HEAD
790 + [0.36.2]: https://github.com/philss/floki/compare/v0.36.1...v0.36.2
774 791 [0.36.1]: https://github.com/philss/floki/compare/v0.36.0...v0.36.1
775 792 [0.36.0]: https://github.com/philss/floki/compare/v0.35.4...v0.36.0
776 793 [0.35.4]: https://github.com/philss/floki/compare/v0.35.3...v0.35.4
  @@ -1,37 +1,36 @@
1 + {<<"app">>,<<"floki">>}.
2 + {<<"build_tools">>,[<<"mix">>]}.
3 + {<<"description">>,
4 + <<"Floki is a simple HTML parser that enables search for nodes using CSS selectors.">>}.
5 + {<<"elixir">>,<<"~> 1.13">>}.
6 + {<<"files">>,
7 + [<<"lib/floki">>,<<"lib/floki/html_tree.ex">>,<<"lib/floki/html_parser">>,
8 + <<"lib/floki/html_parser/html5ever.ex">>,
9 + <<"lib/floki/html_parser/mochiweb.ex">>,
10 + <<"lib/floki/html_parser/fast_html.ex">>,<<"lib/floki/traversal.ex">>,
11 + <<"lib/floki/html_tree">>,<<"lib/floki/html_tree/text.ex">>,
12 + <<"lib/floki/html_tree/html_node.ex">>,<<"lib/floki/html_tree/comment.ex">>,
13 + <<"lib/floki/html_tree/id_seeder.ex">>,<<"lib/floki/selector.ex">>,
14 + <<"lib/floki/entities.ex">>,<<"lib/floki/deep_text.ex">>,
15 + <<"lib/floki/flat_text.ex">>,<<"lib/floki/finder.ex">>,
16 + <<"lib/floki/entities">>,<<"lib/floki/entities/codepoints.ex">>,
17 + <<"lib/floki/filter_out.ex">>,<<"lib/floki/html_parser.ex">>,
18 + <<"lib/floki/selector">>,<<"lib/floki/selector/pseudo_class.ex">>,
19 + <<"lib/floki/selector/attribute_selector.ex">>,
20 + <<"lib/floki/selector/functional.ex">>,
21 + <<"lib/floki/selector/combinator.ex">>,<<"lib/floki/selector/parser.ex">>,
22 + <<"lib/floki/selector/tokenizer.ex">>,<<"lib/floki/raw_html.ex">>,
23 + <<"lib/floki/html">>,<<"lib/floki/html/numeric_charref.ex">>,
24 + <<"lib/floki/html/tokenizer.ex">>,<<"lib/floki/text_extractor.ex">>,
25 + <<"lib/floki/parse_error.ex">>,<<"lib/floki.ex">>,
26 + <<"src/floki_selector_lexer.xrl">>,<<"src/floki_mochi_html.erl">>,
27 + <<"mix.exs">>,<<"README.md">>,<<"LICENSE">>,<<"CODE_OF_CONDUCT.md">>,
28 + <<"CONTRIBUTING.md">>,<<"CHANGELOG.md">>]}.
29 + {<<"licenses">>,[<<"MIT">>]}.
1 30 {<<"links">>,
2 31 [{<<"Changelog">>,<<"https://hexdocs.pm/floki/changelog.html">>},
3 32 {<<"GitHub">>,<<"https://github.com/philss/floki">>},
4 33 {<<"Sponsor">>,<<"https://github.com/sponsors/philss">>}]}.
5 34 {<<"name">>,<<"floki">>}.
6 - {<<"version">>,<<"0.36.1">>}.
7 - {<<"description">>,
8 - <<"Floki is a simple HTML parser that enables search for nodes using CSS selectors.">>}.
9 - {<<"elixir">>,<<"~> 1.13">>}.
10 - {<<"app">>,<<"floki">>}.
11 - {<<"licenses">>,[<<"MIT">>]}.
12 - {<<"files">>,
13 - [<<"lib/floki">>,<<"lib/floki/html_parser">>,
14 - <<"lib/floki/html_parser/html5ever.ex">>,
15 - <<"lib/floki/html_parser/fast_html.ex">>,
16 - <<"lib/floki/html_parser/mochiweb.ex">>,<<"lib/floki/traversal.ex">>,
17 - <<"lib/floki/text_extractor.ex">>,<<"lib/floki/raw_html.ex">>,
18 - <<"lib/floki/selector.ex">>,<<"lib/floki/selector">>,
19 - <<"lib/floki/selector/combinator.ex">>,
20 - <<"lib/floki/selector/attribute_selector.ex">>,
21 - <<"lib/floki/selector/tokenizer.ex">>,<<"lib/floki/selector/parser.ex">>,
22 - <<"lib/floki/selector/functional.ex">>,
23 - <<"lib/floki/selector/pseudo_class.ex">>,<<"lib/floki/html_tree">>,
24 - <<"lib/floki/html_tree/id_seeder.ex">>,<<"lib/floki/html_tree/comment.ex">>,
25 - <<"lib/floki/html_tree/html_node.ex">>,<<"lib/floki/html_tree/text.ex">>,
26 - <<"lib/floki/finder.ex">>,<<"lib/floki/filter_out.ex">>,
27 - <<"lib/floki/html_tree.ex">>,<<"lib/floki/html">>,
28 - <<"lib/floki/html/numeric_charref.ex">>,<<"lib/floki/html/tokenizer.ex">>,
29 - <<"lib/floki/html_parser.ex">>,<<"lib/floki/deep_text.ex">>,
30 - <<"lib/floki/entities.ex">>,<<"lib/floki/flat_text.ex">>,
31 - <<"lib/floki/parse_error.ex">>,<<"lib/floki/entities">>,
32 - <<"lib/floki/entities/codepoints.ex">>,<<"lib/floki.ex">>,
33 - <<"src/floki_selector_lexer.xrl">>,<<"src/floki_mochi_html.erl">>,
34 - <<"mix.exs">>,<<"README.md">>,<<"LICENSE">>,<<"CODE_OF_CONDUCT.md">>,
35 - <<"CONTRIBUTING.md">>,<<"CHANGELOG.md">>]}.
36 35 {<<"requirements">>,[]}.
37 - {<<"build_tools">>,[<<"mix">>]}.
36 + {<<"version">>,<<"0.36.2">>}.
  @@ -328,4 +328,77 @@ defmodule Floki.HTMLTree do
328 328 do_reduce(tree, fun.(head_node, acc), fun)
329 329 end
330 330 end
331 +
332 + defimpl Inspect do
333 + import Inspect.Algebra
334 +
335 + def inspect(html_tree, opts) do
336 + open = "#Floki.HTMLTree["
337 + close = "]"
338 + container_opts = [separator: "", break: :flex]
339 +
340 + container_doc(
341 + open,
342 + nodes_with_tree(html_tree, html_tree.root_nodes_ids),
343 + close,
344 + opts,
345 + &fun/2,
346 + container_opts
347 + )
348 + end
349 +
350 + defp fun({html_tree, %HTMLNode{} = html_node}, opts) do
351 + {open, close, container_opts} = build_node(html_node, opts)
352 +
353 + container_doc(
354 + open,
355 + nodes_with_tree(html_tree, html_node.children_nodes_ids),
356 + close,
357 + opts,
358 + &fun/2,
359 + container_opts
360 + )
361 + end
362 +
363 + defp fun(%Comment{content: comment}, opts),
364 + do: color(concat(["<!-- ", comment, " -->"]), :comment, opts)
365 +
366 + defp fun(%Text{content: text}, opts), do: color(text, :string, opts)
367 +
368 + defp nodes_with_tree(html_tree, nodes_ids) do
369 + nodes_ids
370 + |> Enum.reverse()
371 + |> Enum.map(fn node_id ->
372 + with %HTMLNode{} = html_node <- Map.get(html_tree.nodes, node_id) do
373 + {html_tree, html_node}
374 + end
375 + end)
376 + end
377 +
378 + defp build_node(%HTMLNode{} = node, opts) do
379 + tag_color = :map
380 + attribute_color = :map
381 +
382 + built_attributes =
383 + for {name, value} <- node.attributes do
384 + concat([
385 + color(" #{name}=", attribute_color, opts),
386 + color("\"#{value}\"", :string, opts)
387 + ])
388 + end
389 + |> concat()
390 +
391 + open =
392 + concat([
393 + color("<#{node.type}", tag_color, opts),
394 + built_attributes,
395 + color(">", tag_color, opts)
396 + ])
397 +
398 + close = color("</#{node.type}>", tag_color, opts)
399 + container_opts = [separator: "", break: :strict]
400 +
401 + {open, close, container_opts}
402 + end
403 + end
331 404 end
  @@ -35,13 +35,12 @@ defmodule Floki.RawHTML do
35 35 @no_encoder &Function.identity/1
36 36
37 37 def raw_html(html_tree, opts) do
38 - opts = Keyword.validate!(opts, encode: true, pretty: false)
38 + opts = Keyword.validate!(opts, encode: use_default_encoder?(), pretty: false)
39 39
40 40 encoder =
41 41 case opts[:encode] do
42 42 true -> @encoder
43 43 false -> @no_encoder
44 - :error -> default_encoder()
45 44 end
46 45
47 46 padding =
  @@ -178,6 +177,7 @@ defmodule Floki.RawHTML do
178 177 case type do
179 178 "script" -> @no_encoder
180 179 "style" -> @no_encoder
180 + "title" -> @no_encoder
181 181 _ -> encoder
182 182 end
183 183
  @@ -195,12 +195,8 @@ defmodule Floki.RawHTML do
195 195 ]
196 196 end
197 197
198 - defp default_encoder do
199 - if Application.get_env(:floki, :encode_raw_html, true) do
200 - @encoder
201 - else
202 - @no_encoder
203 - end
198 + defp use_default_encoder? do
199 + Application.get_env(:floki, :encode_raw_html, true)
204 200 end
205 201
206 202 # helpers
  @@ -3,7 +3,7 @@ defmodule Floki.Mixfile do
3 3
4 4 @description "Floki is a simple HTML parser that enables search for nodes using CSS selectors."
5 5 @source_url "https://github.com/philss/floki"
6 - @version "0.36.1"
6 + @version "0.36.2"
7 7
8 8 def project do
9 9 [
  @@ -45,7 +45,7 @@ defmodule Floki.Mixfile do
45 45 [
46 46 {:jason, "~> 1.1", only: [:dev, :test, :docs]},
47 47 {:earmark, "~> 1.2", only: :dev},
48 - {:ex_doc, "~> 0.31.0", only: :dev, runtime: false},
48 + {:ex_doc, "~> 0.32.0", only: :dev, runtime: false},
49 49 {:benchee, "~> 1.3.0", only: :dev},
50 50 {:benchee_html, "~> 1.0", only: :dev},
51 51 {:credo, ">= 0.0.0", only: [:dev, :test]},