Merge branch 'master' into raw

.github/workflows/elixir.yml

@@ -10,7 +10,7 @@ jobs:
   build:
 
     name: Build and test
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-20.04
 
     steps:
     - name: Check out the repository

.gitignore

@@ -25,4 +25,5 @@ onigumo-*.tar
 # Temporary files, for example, from tests.
 /tmp/
 
-onigumo
+# Ignore onigumo escript file
+/onigumo

README.md

@@ -26,13 +26,13 @@ flowchart LR
 
     onigumo_operator           -->         spider_materialization[MATERIALIZER]
 	
-	subgraph Onigumo
+	subgraph "Onigumo (kernel)"
 	    onigumo_operator
 		onigumo_downloader
 		onigumo_parser
 	end
 
-    subgraph Spider
+    subgraph "Spider (application)"
        spider_operator
        spider_parser
        spider_materialization
@@ -51,14 +51,14 @@ The Operator’s job is to:
 
 ### Downloader ###
 
-Stahuje obsah a metadata nezpracovaných URL adres.
+The Downloader fetches and saves the contents and metadata from the unprocessed URL addresses.
 
-Činnost _downloaderu_ se skládá z:
+The Downloader’s job is to:
 
-1. načítání URL ke stažení,
-2. kontroly stažených URL,
-3. stahování obsahu URL a případných metadat,
-4. uložení stažených dat.
+1. read URLs for download,
+2. check for the already downloaded URLs,
+3. fetch the URLs contents along with its metadata,
+4. save the downloaded data.
 
 ### Parser ###
 

lib/cli.ex

@@ -0,0 +1,7 @@
+defmodule Onigumo.CLI do
+  def main([component]) do
+    module = Module.safe_concat("Onigumo", component)
+    root_path = File.cwd!()
+    module.main(root_path)
+  end
+end

lib/onigumo.ex → lib/onigumo/downloader.ex

@@ -6,11 +6,11 @@ defmodule Onigumo.Downloader do
   def main(root_path) do
     http_client().start()
 
-    download_urls_from_file(root_path)
+    create_download_stream(root_path)
     |> Stream.run()
   end
 
-  def download_urls_from_file(root_path) do
+  def create_download_stream(root_path) do
     root_path
     |> load_urls()
     |> Stream.map(&download_url(&1, root_path))
@@ -51,7 +51,7 @@ defmodule Onigumo.Downloader do
 
   def create_file_name(url) do
     suffix = Application.get_env(:onigumo, :downloaded_suffix)
-    Hash.md5(url, :hex) <> suffix
+    Onigumo.Utilities.Hash.md5(url, :hex) <> suffix
   end
 
   defp http_client() do

lib/spider/html.ex

@@ -0,0 +1,7 @@
+defmodule Onigumo.Spider.HTML do
+  def find_links(document) do
+    Floki.parse_document!(document)
+    |> Floki.find("a")
+    |> Floki.attribute("href")
+  end
+end

lib/hash.ex → lib/utilities/hash.ex

@@ -1,4 +1,4 @@
-defmodule Hash do
+defmodule Onigumo.Utilities.Hash do
   def md5(data, fmt) do
     hash(:md5, data)
     |> format(fmt)

mix.exs

@@ -25,7 +25,10 @@ defmodule Onigumo.MixProject do
       # {:dep_from_hexpm, "~> 0.3.0"},
       # {:dep_from_git, git: "https://github.com/elixir-lang/my_dep.git", tag: "0.1.0"},
       {:httpoison, "~> 1.8"},
-      {:mox, "~> 1.0", only: :test}
+      {:mox, "~> 1.0", only: :test},
+
+      # Spider toolbox dependencies
+      {:floki, "~> 0.32"}
     ]
   end
 

mix.lock

@@ -1,6 +1,8 @@
 %{
   "certifi": {:hex, :certifi, "2.8.0", "d4fb0a6bb20b7c9c3643e22507e42f356ac090a1dcea9ab99e27e0376d695eba", [:rebar3], [], "hexpm", "6ac7efc1c6f8600b08d625292d4bbf584e14847ce1b6b5c44d983d273e1097ea"},
+  "floki": {:hex, :floki, "0.32.1", "dfe3b8db3b793939c264e6f785bca01753d17318d144bd44b407fb3493acaa87", [:mix], [{:html_entities, "~> 0.5.0", [hex: :html_entities, repo: "hexpm", optional: false]}], "hexpm", "d4b91c713e4a784a3f7b1e3cc016eefc619f6b1c3898464222867cafd3c681a3"},
   "hackney": {:hex, :hackney, "1.18.0", "c4443d960bb9fba6d01161d01cd81173089686717d9490e5d3606644c48d121f", [:rebar3], [{:certifi, "~>2.8.0", [hex: :certifi, repo: "hexpm", optional: false]}, {:idna, "~>6.1.0", [hex: :idna, repo: "hexpm", optional: false]}, {:metrics, "~>1.0.0", [hex: :metrics, repo: "hexpm", optional: false]}, {:mimerl, "~>1.1", [hex: :mimerl, repo: "hexpm", optional: false]}, {:parse_trans, "3.3.1", [hex: :parse_trans, repo: "hexpm", optional: false]}, {:ssl_verify_fun, "~>1.1.0", [hex: :ssl_verify_fun, repo: "hexpm", optional: false]}, {:unicode_util_compat, "~>0.7.0", [hex: :unicode_util_compat, repo: "hexpm", optional: false]}], "hexpm", "9afcda620704d720db8c6a3123e9848d09c87586dc1c10479c42627b905b5c5e"},
+  "html_entities": {:hex, :html_entities, "0.5.2", "9e47e70598da7de2a9ff6af8758399251db6dbb7eebe2b013f2bbd2515895c3c", [:mix], [], "hexpm", "c53ba390403485615623b9531e97696f076ed415e8d8058b1dbaa28181f4fdcc"},
   "httpoison": {:hex, :httpoison, "1.8.0", "6b85dea15820b7804ef607ff78406ab449dd78bed923a49c7160e1886e987a3d", [:mix], [{:hackney, "~> 1.17", [hex: :hackney, repo: "hexpm", optional: false]}], "hexpm", "28089eaa98cf90c66265b6b5ad87c59a3729bea2e74e9d08f9b51eb9729b3c3a"},
   "idna": {:hex, :idna, "6.1.1", "8a63070e9f7d0c62eb9d9fcb360a7de382448200fbbd1b106cc96d3d8099df8d", [:rebar3], [{:unicode_util_compat, "~>0.7.0", [hex: :unicode_util_compat, repo: "hexpm", optional: false]}], "hexpm", "92376eb7894412ed19ac475e4a86f7b413c1b9fbb5bd16dccd57934157944cea"},
   "metrics": {:hex, :metrics, "1.0.1", "25f094dea2cda98213cecc3aeff09e940299d950904393b2a29d191c346a8486", [:rebar3], [], "hexpm", "69b09adddc4f74a40716ae54d140f93beb0fb8978d8636eaded0c31b6f099f16"},

test/hash_test.exs

@@ -51,31 +51,31 @@ defmodule HashTest do
     }
   ]
 
-  test("hash MD5 known value in hexadecimal") do
-    for {data, hash_hex, _} <- @known_md5s do
-      hash = Hash.md5(data, :hex)
-      assert(hash == hash_hex)
+  for {data, hash_hex, _} <- @known_md5s do
+    test("hash MD5 #{inspect(data)} in hexadecimal") do
+      hash = Onigumo.Utilities.Hash.md5(unquote(data), :hex)
+      assert(hash == unquote(hash_hex))
     end
   end
 
-  test("hash MD5 known value in binary") do
-    for {data, _, hash_bin} <- @known_md5s do
-      hash = Hash.md5(data, :bin)
-      assert(hash == hash_bin)
+  for {data, _, hash_bin} <- @known_md5s do
+    test("hash MD5 #{inspect(data)} in binary") do
+      hash = Onigumo.Utilities.Hash.md5(unquote(data), :bin)
+      assert(hash == unquote(hash_bin))
     end
   end
 
-  test("format a binary hash") do
-    for {format, hash} <- @formatted_hashes do
-      formatted = Hash.format(@binary_hash, format)
-      assert(formatted == hash)
+  for {format, hash} <- @formatted_hashes do
+    test("format #{inspect(@binary_hash)} in #{inspect(format)}") do
+      formatted = Onigumo.Utilities.Hash.format(@binary_hash, unquote(format))
+      assert(formatted == unquote(hash))
     end
   end
 
-  test("hash a known value") do
-    for {func, known_hash} <- @known_hashes do
-      computed_hash = Hash.hash(func, @known_hash_data)
-      assert(computed_hash == known_hash)
+  for {func, known_hash} <- @known_hashes do
+    test("hash #{inspect(@known_hash_data)} with #{inspect(func)}") do
+      computed_hash = Onigumo.Utilities.Hash.hash(unquote(func), @known_hash_data)
+      assert(computed_hash == unquote(known_hash))
     end
   end
 end

test/onigumo_downloader_test.exs

@@ -0,0 +1,150 @@
+defmodule OnigumoDownloaderTest do
+  use ExUnit.Case
+  import Mox
+
+  @urls [
+    "http://onigumo.local/hello.html",
+    "http://onigumo.local/bye.html"
+  ]
+  @slices [0..1, 0..-1]
+
+  setup(:verify_on_exit!)
+
+  describe("Onigumo.Downloader.main/1") do
+    @tag :tmp_dir
+    test("run Downloader", %{tmp_dir: tmp_dir}) do
+      expect(HTTPoisonMock, :start, fn -> nil end)
+      expect(HTTPoisonMock, :get!, length(@urls), &prepare_response/1)
+
+      input_path_env = Application.get_env(:onigumo, :input_path)
+      input_path_tmp = Path.join(tmp_dir, input_path_env)
+      input_file_content = prepare_input(@urls)
+      File.write!(input_path_tmp, input_file_content)
+
+      Onigumo.Downloader.main(tmp_dir)
+
+      Enum.map(@urls, &assert_downloaded(&1, tmp_dir))
+    end
+  end
+
+  describe("Onigumo.Downloader.create_download_stream/1") do
+    @tag :tmp_dir
+    test("download URLs from the input file with a created stream", %{tmp_dir: tmp_dir}) do
+      expect(HTTPoisonMock, :get!, length(@urls), &prepare_response/1)
+
+      input_path_env = Application.get_env(:onigumo, :input_path)
+      input_path_tmp = Path.join(tmp_dir, input_path_env)
+      input_file_content = prepare_input(@urls)
+      File.write!(input_path_tmp, input_file_content)
+
+      Onigumo.Downloader.create_download_stream(tmp_dir) |> Stream.run()
+
+      Enum.map(@urls, &assert_downloaded(&1, tmp_dir))
+    end
+  end
+
+  describe("Onigumo.Downloader.download_url/2") do
+    @tag :tmp_dir
+    test("download a URL", %{tmp_dir: tmp_dir}) do
+      expect(HTTPoisonMock, :get!, &prepare_response/1)
+
+      input_url = Enum.at(@urls, 0)
+      Onigumo.Downloader.download_url(input_url, tmp_dir)
+
+      output_file_name = Onigumo.Downloader.create_file_name(input_url)
+      output_path = Path.join(tmp_dir, output_file_name)
+      read_output = File.read!(output_path)
+      expected_output = body(input_url)
+      assert(read_output == expected_output)
+    end
+  end
+
+  describe("Onigumo.Downloader.get_url/1") do
+    test("get response by HTTP request") do
+      expect(HTTPoisonMock, :get!, &prepare_response/1)
+
+      url = Enum.at(@urls, 0)
+      get_response = Onigumo.Downloader.get_url(url)
+      expected_response = prepare_response(url)
+      assert(get_response == expected_response)
+    end
+  end
+
+  describe("Onigumo.Downloader.get_body/1") do
+    test("extract body from URL response") do
+      url = Enum.at(@urls, 0)
+      response = prepare_response(url)
+      get_body = Onigumo.Downloader.get_body(response)
+      expected_body = body(url)
+      assert(get_body == expected_body)
+    end
+  end
+
+  describe("Onigumo.Downloader.write_response/2") do
+    @tag :tmp_dir
+    test("write response to file", %{tmp_dir: tmp_dir}) do
+      response = "Response!"
+      output_file_name = "body.html"
+      output_path = Path.join(tmp_dir, output_file_name)
+      Onigumo.Downloader.write_response(response, output_path)
+
+      read_output = File.read!(output_path)
+      assert(read_output == response)
+    end
+  end
+
+  describe("Onigumo.Downloader.load_urls/1") do
+    for slice <- @slices do
+      @tag :tmp_dir
+      test("load URLs #{inspect(slice)} from a file", %{tmp_dir: tmp_dir}) do
+        input_urls = Enum.slice(@urls, unquote(Macro.escape(slice)))
+
+        input_path_env = Application.get_env(:onigumo, :input_path)
+        input_path_tmp = Path.join(tmp_dir, input_path_env)
+        input_file_content = prepare_input(input_urls)
+        File.write!(input_path_tmp, input_file_content)
+
+        loaded_urls = Onigumo.Downloader.load_urls(tmp_dir) |> Enum.to_list()
+
+        assert(loaded_urls == input_urls)
+      end
+    end
+  end
+
+  describe("Onigumo.Downloader.create_file_name/1") do
+    test("create file name from URL") do
+      input_url = "https://onigumo.local/hello.html"
+      created_file_name = Onigumo.Downloader.create_file_name(input_url)
+
+      input_url_hash = Hash.md5(input_url, :hex)
+      downloaded_suffix = Application.get_env(:onigumo, :downloaded_suffix)
+      expected_file_name = input_url_hash <> downloaded_suffix
+
+      assert(created_file_name == expected_file_name)
+    end
+  end
+
+  defp prepare_response(url) do
+    %HTTPoison.Response{
+      status_code: 200,
+      body: body(url)
+    }
+  end
+
+  defp prepare_input(urls) do
+    Enum.map(urls, &(&1 <> "\n"))
+    |> Enum.join()
+  end
+
+  defp body(url) do
+    "Body from: #{url}\n"
+  end
+
+  defp assert_downloaded(url, tmp_dir) do
+    file_name = Onigumo.Downloader.create_file_name(url)
+    output_path = Path.join(tmp_dir, file_name)
+    read_output = File.read!(output_path)
+    expected_output = body(url)
+    assert(read_output == expected_output)
+  end
+end