add Elixir version

Author: hipertracker

.gitignore

@@ -2,3 +2,5 @@
 /.vscode/
 /.DS_Store
 
+/words_extractor_jl/
+/words_extractor_pypy/

README.md

@@ -4,16 +4,17 @@ Example of words extracting in Go, Crystal, Rust and Python
 
 Text source: 79.4MB in 30 files
 
-- Python 3.9.5 (parallel) with sorting: 4.01s, without sorting: 2.47
+- Python 3.9.5 (parallel) with sorting: 3.42s, without sorting: 2.47
 - Go 1.16.4 (parallel) with sorting: 7.32s, without sorting: 4.06s
 - Python 3.9.5 with sorting: 10s, without sorting 8.32s
 - Go 1.16.4 with sorting: 21s, without sorting: 11s
+- Elixir 1.12 (parallel) with sorting: 33s
 - Rust 1.51.0 with sorting: 1m31s, without sorting: 1m10s
 - Crystal 1.0.0 with sorting: 2m55s, without sorting: 27s
 
 macOS 11.3.1, MacBook Pro (Retina, 15-inch, Late 2013)
 
-```
+```bash
 cd words_extractor_py
 python words.py
 
@@ -25,14 +26,17 @@ make run
 
 cd words_extractor_cr
 crystal run src/fast_words_cr.cr
+
+cd words_extractor_ex
+mix run "WordExtractor.run"
 ```
 
 ## Running Python
 
 1. Install the latest Python 3.9.5
 2. Create venv and dependencies
 
-```
+```bash
 cd words_extractor_py
 python -m venv venv
 source venv/bin/activate
@@ -41,6 +45,6 @@ pip install -r requirements.txt
 
 3. Run the code
 
-```
+```bash
 python words_parallel.py
 ```

words_extractor_ex/.formatter.exs

@@ -0,0 +1,4 @@
+# Used by "mix format"
+[
+  inputs: ["{mix,.formatter}.exs", "{config,lib,test}/**/*.{ex,exs}"]
+]

words_extractor_ex/.gitignore

@@ -0,0 +1,29 @@
+# The directory Mix will write compiled artifacts to.
+/_build/
+
+# If you run "mix test --cover", coverage assets end up here.
+/cover/
+
+# The directory Mix downloads your dependencies sources to.
+/deps/
+
+# Where third-party dependencies like ExDoc output generated docs.
+/doc/
+
+# Ignore .fetch files in case you like to edit your project deps locally.
+/.fetch
+
+# If the VM crashes, it generates a dump, let's ignore it too.
+erl_crash.dump
+
+# Also ignore archive artifacts (built via "mix archive.build").
+*.ez
+
+# Ignore package tarball (built via "mix hex.build").
+words_extractor_ex-*.tar
+
+# Temporary files, for example, from tests.
+/tmp/
+/.elixir_ls/
+/.history/
+/.ipynb_checkpoints/

words_extractor_ex/README.md

@@ -0,0 +1,21 @@
+# WordsExtractor
+
+**TODO: Add description**
+
+## Installation
+
+If [available in Hex](https://hex.pm/docs/publish), the package can be installed
+by adding `words_extractor_ex` to your list of dependencies in `mix.exs`:
+
+```elixir
+def deps do
+  [
+    {:words_extractor_ex, "~> 0.1.0"}
+  ]
+end
+```
+
+Documentation can be generated with [ExDoc](https://github.com/elixir-lang/ex_doc)
+and published on [HexDocs](https://hexdocs.pm). Once published, the docs can
+be found at [https://hexdocs.pm/words_extractor_ex](https://hexdocs.pm/words_extractor_ex).
+

words_extractor_ex/lib/words_extractor.ex

@@ -0,0 +1,47 @@
+defmodule WordsExtractor do
+  @moduledoc nil
+
+  def run do
+    outdir = "words"
+    clean_dir(outdir)
+
+    walk("../data/pl/", ".yml")
+    |> Task.async_stream(
+      WordsExtractor,
+      :worker,
+      [outdir],
+      ordered: false,
+      timeout: :infinity
+    )
+    |> Enum.to_list()
+  end
+
+  def clean_dir(path) do
+    File.rm_rf!(path)
+    File.mkdir!(path)
+  end
+
+  def worker(path, outdir) do
+    %{"code" => code} = YamlElixir.read_from_file!(path)
+
+    words =
+      File.read!(String.replace(path, ".yml", ".txt"))
+      |> String.downcase()
+      |> String.trim()
+      |> then(&Regex.split(~r/[\W\d]+/u, &1))
+      |> MapSet.new()
+      # sorting does not respect collation
+      |> Enum.sort()
+
+    File.write!("#{outdir}/extracted-#{code}.txt", Enum.join(words, "\n"))
+    IO.puts(path)
+  end
+
+  def walk(path, pattern) do
+    dir = String.to_charlist(path)
+    regexp = String.to_charlist(pattern)
+
+    :filelib.fold_files(dir, regexp, true, fn file, acc -> [file | acc] end, [])
+    |> Enum.map(fn filepath -> to_string(filepath) end)
+  end
+end

words_extractor_ex/mix.exs

@@ -0,0 +1,29 @@
+defmodule WordsExtractor.MixProject do
+  use Mix.Project
+
+  def project do
+    [
+      app: :words_extractor_ex,
+      version: "0.1.0",
+      elixir: "~> 1.12",
+      start_permanent: Mix.env() == :prod,
+      deps: deps()
+    ]
+  end
+
+  # Run "mix help compile.app" to learn about applications.
+  def application do
+    [
+      extra_applications: [:logger]
+    ]
+  end
+
+  # Run "mix help deps" to learn about dependencies.
+  defp deps do
+    [
+      {:yaml_elixir, "~> 2.7"}
+      # {:dep_from_hexpm, "~> 0.3.0"},
+      # {:dep_from_git, git: "https://github.com/elixir-lang/my_dep.git", tag: "0.1.0"}
+    ]
+  end
+end

words_extractor_ex/mix.lock

@@ -0,0 +1,4 @@
+%{
+  "yamerl": {:hex, :yamerl, "0.8.1", "07da13ffa1d8e13948943789665c62ccd679dfa7b324a4a2ed3149df17f453a4", [:rebar3], [], "hexpm", "96cb30f9d64344fed0ef8a92e9f16f207de6c04dfff4f366752ca79f5bceb23f"},
+  "yaml_elixir": {:hex, :yaml_elixir, "2.7.0", "6f731d622a3b28769e26e634f82aa171d1d01cae0e8820ce9e93e559c83c23c8", [:mix], [{:yamerl, "~> 0.8", [hex: :yamerl, repo: "hexpm", optional: false]}], "hexpm", "f2eb39e0fb23625777f74e0c821f42f033dc4eaa5402c34beaa665944d85f3ea"},
+}

words_extractor_ex/test/test_helper.exs

@@ -0,0 +1 @@
+ExUnit.start()

words_extractor_ex/test/words_extractor_test.exs

@@ -0,0 +1,8 @@
+defmodule WordsExtractorTest do
+  use ExUnit.Case
+  doctest WordsExtractor
+
+  # test "greets the world" do
+  #   assert WordsExtractor.hello() == :world
+  # end
+end