carpodaster/latin1encoding_part1.ex

## latin1encoding_part1.ex
defmodule Latin1Convert do

  @doc """
  Convert an input HTML string to UTF-8 unicode.
  """
  @spec call(String.t) :: String.t
  def call(html) do
    content_type = content_type_from_header(html)
    cond do
      content_type == :latin1 ->
        html
        |> :unicode.characters_to_binary(:latin1)
        |> remove_meta_http_equiv_encoding
      true ->
        html
    end
  end

  @doc """
  Looks for a <meta http-equiv="Content-Type"> node in the input
  string's HTML header and returns an atom representing the encoding.
  """
  @spec content_type_from_header(String.t) :: atom | nil
  def content_type_from_header(html) do
    encoding = meta_http_equiv_encoding(html)

    cond do
      Regex.match?(~r(iso-8859)i, encoding) ->
        :latin1
      Regex.match?(~r(utf-8)i, encoding) ->
        :unicode
      true ->
        nil
    end
  end

  @doc """
  Retrieves the content type indication from `html`.

  iex>"<html><head><meta http-equiv=\"Content-Type\" content=\"text/html; charset=ISO-8859-1\"></head></html>" |> Latin1Convert.meta_http_equiv_encoding
  "text/html; charset=ISO-8859-1"

  iex>Latin1Convert.meta_http_equiv_encoding("<html></html>")
  ""
  """
  @spec meta_http_equiv_encoding(String.t) :: String.t
  def meta_http_equiv_encoding(html) do
    String.downcase(html)
    |> Floki.attribute("head > meta[http-equiv=content-type]", "content")
    |> List.first
    |> to_string
  end

  # Caveat: not really case-sensitive check for the DOM node.
  # Floki doesn't seem to understand `$=foo i` queries. We can't
  # `String.downcase` here as that will mess up the filter chain.
  defp remove_meta_http_equiv_encoding(html) do
    Floki.filter_out(html, "head > meta[http-equiv*=ontent-]")
    |> Floki.raw_html
  end
end
	defmodule Latin1Convert do

	@doc """
	Convert an input HTML string to UTF-8 unicode.
	"""
	@spec call(String.t) :: String.t
	def call(html) do
	content_type = content_type_from_header(html)
	cond do
	content_type == :latin1 ->
	html
	\|> :unicode.characters_to_binary(:latin1)
	\|> remove_meta_http_equiv_encoding
	true ->
	html
	end
	end

	@doc """
	Looks for a <meta http-equiv="Content-Type"> node in the input
	string's HTML header and returns an atom representing the encoding.
	"""
	@spec content_type_from_header(String.t) :: atom \| nil
	def content_type_from_header(html) do
	encoding = meta_http_equiv_encoding(html)

	cond do
	Regex.match?(~r(iso-8859)i, encoding) ->
	:latin1
	Regex.match?(~r(utf-8)i, encoding) ->
	:unicode
	true ->
	nil
	end
	end

	@doc """
	Retrieves the content type indication from `html`.

	iex>"<html><head><meta http-equiv=\"Content-Type\" content=\"text/html; charset=ISO-8859-1\"></head></html>" \|> Latin1Convert.meta_http_equiv_encoding
	"text/html; charset=ISO-8859-1"

	iex>Latin1Convert.meta_http_equiv_encoding("<html></html>")
	""
	"""
	@spec meta_http_equiv_encoding(String.t) :: String.t
	def meta_http_equiv_encoding(html) do
	String.downcase(html)
	\|> Floki.attribute("head > meta[http-equiv=content-type]", "content")
	\|> List.first
	\|> to_string
	end

	# Caveat: not really case-sensitive check for the DOM node.
	# Floki doesn't seem to understand `$=foo i` queries. We can't
	# `String.downcase` here as that will mess up the filter chain.
	defp remove_meta_http_equiv_encoding(html) do
	Floki.filter_out(html, "head > meta[http-equiv*=ontent-]")
	\|> Floki.raw_html
	end
	end