Page MenuHomePhorge
Files F85651256

No OneTemporary
Actions

Size
4 KB
Referenced Files
None
Subscribers
None

View Options

diff --git a/lib/fast_html.ex b/lib/fast_html.ex
index 58ec125..387278c 100644
--- a/lib/fast_html.ex
+++ b/lib/fast_html.ex
@@ -1,102 +1,77 @@
defmodule :fast_html do
@moduledoc """
A module to decode html into a tree structure.
Based on [Alexander Borisov's myhtml](https://github.com/lexborisov/myhtml),
this binding gains the properties of being html-spec compliant and very fast.
-
- ## Example
-
- iex> :fast_html.decode("<h1>Hello world</h1>")
- {:ok, {"html", [], [{"head", [], []}, {"body", [], [{"h1", [], ["Hello world"]}]}]}}
-
- Benchmark results (removed Nif calling mode) on various file sizes on a 2,5Ghz Core i7:
-
- Settings:
- duration: 1.0 s
-
- ## FileSizesBench
- [15:28:42] 1/3: github_trending_js.html 341k
- [15:28:46] 2/3: w3c_html5.html 131k
- [15:28:48] 3/3: wikipedia_hyperlink.html 97k
-
- Finished in 7.52 seconds
-
- ## FileSizesBench
- benchmark name iterations average time
- wikipedia_hyperlink.html 97k 1000 1385.86 µs/op
- w3c_html5.html 131k 1000 2179.30 µs/op
- github_trending_js.html 341k 500 5686.21 µs/op
"""
@type tag() :: String.t() | atom()
@type attr() :: {String.t(), String.t()}
@type attr_list() :: [] | [attr()]
@type comment_node() :: {:comment, String.t()}
@type comment_node3() :: {:comment, [], String.t()}
@type tree() ::
{tag(), attr_list(), tree()}
| {tag(), attr_list(), nil}
| comment_node()
| comment_node3()
@type format_flag() :: :html_atoms | :nil_self_closing | :comment_tuple3
@doc """
Returns a tree representation from the given html string.
- ## Examples
+ `opts` is a keyword list of options, the options available:
+ * `timeout` - Call timeout
+ * `format` - Format flags for the tree
+
+ The following format flags are available:
+
+ * `:html_atoms` uses atoms for known html tags (faster), binaries for everything else.
+ * `:nil_self_closing` uses `nil` to designate self-closing tags and void elements.
+ For example `<br>` is then being represented like `{"br", [], nil}`.
+ See http://w3c.github.io/html-reference/syntax.html#void-elements for a full list of void elements.
+ * `:comment_tuple3` uses 3-tuple elements for comments, instead of the default 2-tuple element.
+ ## Examples
iex> :fast_html.decode("<h1>Hello world</h1>")
{:ok, {"html", [], [{"head", [], []}, {"body", [], [{"h1", [], ["Hello world"]}]}]}}
+ iex> :fast_html.decode("Hello world", timeout: 0)
+ {:error, :timeout}
+
iex> :fast_html.decode("<span class='hello'>Hi there</span>")
{:ok, {"html", [],
[{"head", [], []},
{"body", [], [{"span", [{"class", "hello"}], ["Hi there"]}]}]}}
iex> :fast_html.decode("<body><!-- a comment --!></body>")
{:ok, {"html", [], [{"head", [], []}, {"body", [], [comment: " a comment "]}]}}
iex> :fast_html.decode("<br>")
{:ok, {"html", [], [{"head", [], []}, {"body", [], [{"br", [], []}]}]}}
- """
- @spec decode(String.t()) :: {:ok, tree()} | {:error, String.t() | atom()}
- def decode(bin) do
- decode(bin, format: [])
- end
-
- @doc """
- Returns a tree representation from the given html string.
-
- This variant allows you to pass in one or more of the following format flags:
-
- * `:html_atoms` uses atoms for known html tags (faster), binaries for everything else.
- * `:nil_self_closing` uses `nil` to designate self-closing tags and void elements.
- For example `<br>` is then being represented like `{"br", [], nil}`.
- See http://w3c.github.io/html-reference/syntax.html#void-elements for a full list of void elements.
- * `:comment_tuple3` uses 3-tuple elements for comments, instead of the default 2-tuple element.
-
- ## Examples
iex> :fast_html.decode("<h1>Hello world</h1>", format: [:html_atoms])
{:ok, {:html, [], [{:head, [], []}, {:body, [], [{:h1, [], ["Hello world"]}]}]}}
iex> :fast_html.decode("<br>", format: [:nil_self_closing])
{:ok, {"html", [], [{"head", [], []}, {"body", [], [{"br", [], nil}]}]}}
iex> :fast_html.decode("<body><!-- a comment --!></body>", format: [:comment_tuple3])
{:ok, {"html", [], [{"head", [], []}, {"body", [], [{:comment, [], " a comment "}]}]}}
iex> html = "<body><!-- a comment --!><unknown /></body>"
iex> :fast_html.decode(html, format: [:html_atoms, :nil_self_closing, :comment_tuple3])
{:ok, {:html, [],
[{:head, [], []},
{:body, [], [{:comment, [], " a comment "}, {"unknown", [], nil}]}]}}
"""
@spec decode(String.t(), format: [format_flag()]) ::
{:ok, tree()} | {:error, String.t() | atom()}
- def decode(bin, format: flags) do
- FastHtml.Cnode.call({:decode, bin, flags})
+ def decode(bin, opts \\ []) do
+ flags = Keyword.get(opts, :format, [])
+ timeout = Keyword.get(opts, :timeout, 10000)
+ FastHtml.Cnode.call({:decode, bin, flags}, timeout)
end
end

File Metadata

Mime Type
text/x-diff
Expires
Sun, Aug 30, 3:32 PM (1 d, 17 h)
Storage Engine
blob
Storage Format
Raw Data
Storage Handle
1738050
Default Alt Text
(4 KB)

Event Timeline