searcher.ex

# To run this code, you'll need the sample data (133 MB download, unzips to 492 MB):
#     http://bit.ly/2avfASU
#     tar xjf sample.tar.bz2

defmodule Elindex.Searcher do
  def search(word) do
    File.ls!("sample")
    |> Stream.map(fn(filename) ->
         fn ->
            Path.join("sample", filename)
            |> File.read!
            |> hit_info(word)
         end
       end)
    |> Stream.map(&Task.async/1)
    |> Stream.map(&Task.await/1)
    |> Stream.filter(fn({count, _}) -> count > 0 end)
    |> Enum.sort(&>=/2)
    |> Enum.take(10)
  end

  def hit_info(blob, word) do
    count = Enum.count(Regex.scan(~r(\b#{word}\b), blob))
    title = String.split(blob, "\n") |> List.first
    {count, title}
  end
end