Packages

meeseeks

0.13.1
0.18.0 0.17.0 0.16.1 0.16.0 0.15.1 0.15.0 0.14.0 0.13.1 0.13.0 0.12.0 0.11.2 0.11.1 0.11.0 0.10.1 0.10.0 0.9.5 0.9.4 0.9.3 0.9.2 0.9.1 0.9.0 0.8.0 0.7.7 0.7.6 0.7.5 0.7.4 0.7.3 0.7.2 0.7.1 0.7.0 0.6.0 0.5.0 0.4.1 0.4.0 0.3.1 0.3.0 0.2.1 0.2.0 0.1.0

Meeseeks is a library for parsing and extracting data from HTML and XML with CSS or XPath selectors.

HexDocs

Current section

Files

Jump to
Readme
39 Versions
1 Dependency
Dependants
Files
Activity
meeseeks lib meeseeks document helpers.ex
Raw

lib/meeseeks/document/helpers.ex 

defmodule Meeseeks.Document.Helpers do

  @moduledoc false



  # collapse_whitespace



  def collapse_whitespace(string) do

    String.replace(string, ~r/[\s]+/, " ")

  end



  # html_escape



  def html_escape_attribute_value(attribute_value) do

    html_escape_chars(attribute_value, ["&", "\""])

  end



  def html_escape_text(text) do

    html_escape_chars(text, ["&", "<", ">"])

  end



  defp html_escape_chars(subject, escaped_chars) do

    matches = :binary.matches(subject, escaped_chars)



    subject

    |> do_replace(matches, &html_escape_char/1, 0)

    |> IO.iodata_to_binary()

  end



  defp do_replace(subject, [], _, n) do

    [binary_part(subject, n, byte_size(subject) - n)]

  end



  defp do_replace(subject, [{start, length} | matches], replacement, n) do

    prefix = binary_part(subject, n, start - n)

    middle = replacement.(binary_part(subject, start, length))

    [prefix, middle | do_replace(subject, matches, replacement, start + length)]

  end



  defp html_escape_char("<"), do: "&lt;"

  defp html_escape_char(">"), do: "&gt;"

  defp html_escape_char("&"), do: "&amp;"

  defp html_escape_char("\""), do: "&quot;"

  defp html_escape_char("'"), do: "&#39;"

end