First commit

.circleci/config.yml

@@ -0,0 +1,40 @@
+version: 2
+jobs:
+  build:
+    parallelism: 1
+    docker:
+      - image: circleci/elixir:1.8.0
+        environment:
+          MIX_ENV: test
+    working_directory: ~/app
+    steps:
+      - checkout
+      - run: mix local.hex --force
+      - run: mix local.rebar --force
+      - restore_cache:
+          keys:
+            - v1-mix-cache-{{ .Branch }}-{{ checksum "mix.lock" }}
+            - v1-mix-cache-{{ .Branch }}
+            - v1-mix-cache
+      - restore_cache:
+          keys:
+            - v1-build-cache-{{ .Branch }}
+            - v1-build-cache
+      - run: mix do deps.get, compile
+      - save_cache:
+          key: v1-mix-cache-{{ .Branch }}-{{ checksum "mix.lock" }}
+          paths: "deps"
+      - save_cache:
+          key: v1-mix-cache-{{ .Branch }}
+          paths: "deps"
+      - save_cache:
+          key: v1-mix-cache
+          paths: "deps"
+      - save_cache:
+          key: v1-build-cache-{{ .Branch }}
+          paths: "_build"
+      - save_cache:
+          key: v1-build-cache
+          paths: "_build"
+      - run: mix format --check-formatted
+      - run: mix test

.formatter.exs

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

.gitignore

@@ -0,0 +1,24 @@
+# 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").
+vttyl-*.tar
+

README.md

@@ -0,0 +1,46 @@
+# Vttyl
+
+> A dead simple vtt parser in Elixir.
+
+## Installation
+
+To install Vttyl, add it to your `mix.exs` file.
+
+```elixir
+def deps do
+  [
+    {:vttyl, "~> 0.1.0"}
+  ]
+end
+```
+
+Then, run `$ mix deps.get`.
+
+## Usage
+
+Vttyl has two basic ways to use it.
+
+### String Parsing
+
+```elixir
+iex> vtt = """
+           WEBVTT
+
+           1
+           00:00:15.450 --> 00:00:17.609
+           Hello world!
+           """
+...> Vttyl.parse(vtt)
+[%Vttyl.Part{end: ~T[00:00:17.609], part: 1, start: ~T[00:00:15.450], text: "Hello world!"}]
+```
+
+### Stream Parsing
+
+```elixir
+iex> "same_text.vtt" |> File.stream!([], 2048) |> Vttyl.parse_stream() |> Enum.into([])
+[%Vttyl.Part{end: ~T[00:00:17.609], part: 1, start: ~T[00:00:15.450], text: "Hello world!"}]
+```
+
+For more information, see [the documentation][documentation].
+
+[documentation]: https://hexdocs.pm/vttyl

config/config.exs

@@ -0,0 +1,30 @@
+# This file is responsible for configuring your application
+# and its dependencies with the aid of the Mix.Config module.
+use Mix.Config
+
+# This configuration is loaded before any dependency and is restricted
+# to this project. If another project depends on this project, this
+# file won't be loaded nor affect the parent project. For this reason,
+# if you want to provide default values for your application for
+# third-party users, it should be done in your "mix.exs" file.
+
+# You can configure your application as:
+#
+#     config :vttyl, key: :value
+#
+# and access this configuration in your application as:
+#
+#     Application.get_env(:vttyl, :key)
+#
+# You can also configure a third-party app:
+#
+#     config :logger, level: :info
+#
+
+# It is also possible to import configuration files, relative to this
+# directory. For example, you can emulate configuration per environment
+# by uncommenting the line below and defining dev.exs, test.exs and such.
+# Configuration from the imported file will override the ones defined
+# here (which is why it is important to import them last).
+#
+#     import_config "#{Mix.env()}.exs"

lib/vttyl.ex

@@ -0,0 +1,102 @@
+defmodule Vttyl do
+  @moduledoc """
+  Quick and dirty conveniences for working with utf8 encoded vtt files.
+  """
+
+  alias Vttyl.Part
+
+  @doc """
+  Parse a string.
+
+  This drops badly formatted vtt files. Consult your local doctor to ensure you formatted it correctly.
+  """
+  @spec parse(String.t()) :: [Part.t()]
+  def parse(content) do
+    content
+    |> String.splitter("\n")
+    |> do_parse()
+    |> Enum.into([])
+  end
+
+  @doc """
+  Parse a stream of utf8 encoded characters.
+
+  This returns a stream so you decide how to handle it!
+  """
+  @spec parse_stream(Enumerable.t()) :: Enumerable.t()
+  def parse_stream(content) do
+    content
+    |> Stream.transform("", &next_line/2)
+    |> do_parse()
+  end
+
+  defp do_parse(enum_content) do
+    enum_content
+    |> Stream.map(fn line -> Regex.replace(~r/#.*/, line, "") end)
+    |> Stream.map(&String.trim/1)
+    |> Stream.reject(&(&1 in ["", "WEBVTT"]))
+    |> Stream.chunk_while(%Part{}, &parse_chunk/2, &parse_chunk_after/1)
+    |> Stream.filter(&full_chunk?/1)
+  end
+
+  defp parse_chunk(line, acc) do
+    acc =
+      cond do
+        Regex.match?(~r/^\d+$/, line) ->
+          %Part{acc | part: String.to_integer(line)}
+
+        not is_nil(acc.part) and timestamps?(line) ->
+          {start_ts, end_ts} = parse_timestamps(line)
+
+          %Part{acc | start: start_ts, end: end_ts}
+
+        # Text content should be on one line and the other stuff should have appeared
+        not is_nil(acc.part) and not is_nil(acc.start) and not is_nil(acc.end) and line != "" ->
+          %Part{acc | text: line}
+
+        true ->
+          acc
+      end
+
+    if full_chunk?(acc) do
+      {:cont, acc, %Part{}}
+    else
+      {:cont, acc}
+    end
+  end
+
+  defp parse_chunk_after(acc) do
+    if full_chunk?(acc) do
+      {:cont, acc, %Part{}}
+    else
+      {:cont, acc}
+    end
+  end
+
+  defp full_chunk?(%Part{part: part, start: start, end: ts_end, text: text}) do
+    not is_nil(part) and not is_nil(start) and not is_nil(ts_end) and not is_nil(text)
+  end
+
+  # 00:00:00.000 --> 00:01:01.000
+  defp timestamps?(line) do
+    Regex.match?(~r/(\d{2}:)?\d{2}:\d{2}\.\d{3} --> (\d{2}:)?\d{2}:\d{2}.\d{3}/, line)
+  end
+
+  defp parse_timestamps(line) do
+    line
+    |> String.split("-->")
+    |> Enum.map(fn ts -> ts |> String.trim() |> Time.from_iso8601!() end)
+    |> List.to_tuple()
+  end
+
+  defp next_line(chunk, acc) do
+    case String.split(<<acc::binary, chunk::binary>>, "\n") do
+      [] ->
+        {[], ""}
+
+      lines ->
+        {acc, lines} = List.pop_at(lines, -1)
+        {lines, acc}
+    end
+  end
+end

lib/vttyl/part.ex

@@ -0,0 +1,9 @@
+defmodule Vttyl.Part do
+  @type t :: %__MODULE__{
+          part: non_neg_integer(),
+          start: Time.t(),
+          end: Time.t(),
+          text: String.t()
+        }
+  defstruct [:start, :end, :text, :part]
+end

mix.exs

@@ -0,0 +1,47 @@
+defmodule Vttyl.MixProject do
+  use Mix.Project
+
+  @version "0.1.0"
+  @repo_url "https://github.com/grain-team/vttyl"
+
+  def project do
+    [
+      app: :vttyl,
+      version: @version,
+      elixir: "~> 1.8",
+      start_permanent: Mix.env() == :prod,
+      deps: deps(),
+
+      # Hex
+      package: package(),
+      description: "A dead simple vtt parser.",
+
+      # Docs
+      name: "Vttyl",
+      docs: [
+        source_ref: "v#{@version}",
+        source_url: @repo_url
+      ]
+    ]
+  end
+
+  def application do
+    [
+      extra_applications: [:logger]
+    ]
+  end
+
+  defp package do
+    [
+      licenses: ["MIT"],
+      links: %{"GitHub" => @repo_url}
+    ]
+  end
+
+  defp deps do
+    [
+      {:ex_doc, "~> 0.20", only: :dev},
+      {:dialyxir, "~> 1.0.0-rc.6", only: [:dev, :test], runtime: false}
+    ]
+  end
+end

mix.lock

@@ -0,0 +1,9 @@
+%{
+  "dialyxir": {:hex, :dialyxir, "1.0.0-rc.6", "78e97d9c0ff1b5521dd68041193891aebebce52fc3b93463c0a6806874557d7d", [:mix], [{:erlex, "~> 0.2.1", [hex: :erlex, repo: "hexpm", optional: false]}], "hexpm"},
+  "earmark": {:hex, :earmark, "1.3.2", "b840562ea3d67795ffbb5bd88940b1bed0ed9fa32834915125ea7d02e35888a5", [:mix], [], "hexpm"},
+  "erlex": {:hex, :erlex, "0.2.1", "cee02918660807cbba9a7229cae9b42d1c6143b768c781fa6cee1eaf03ad860b", [:mix], [], "hexpm"},
+  "ex_doc": {:hex, :ex_doc, "0.20.2", "1bd0dfb0304bade58beb77f20f21ee3558cc3c753743ae0ddbb0fd7ba2912331", [:mix], [{:earmark, "~> 1.3", [hex: :earmark, repo: "hexpm", optional: false]}, {:makeup_elixir, "~> 0.10", [hex: :makeup_elixir, repo: "hexpm", optional: false]}], "hexpm"},
+  "makeup": {:hex, :makeup, "0.8.0", "9cf32aea71c7fe0a4b2e9246c2c4978f9070257e5c9ce6d4a28ec450a839b55f", [:mix], [{:nimble_parsec, "~> 0.5.0", [hex: :nimble_parsec, repo: "hexpm", optional: false]}], "hexpm"},
+  "makeup_elixir": {:hex, :makeup_elixir, "0.13.0", "be7a477997dcac2e48a9d695ec730b2d22418292675c75aa2d34ba0909dcdeda", [:mix], [{:makeup, "~> 0.8", [hex: :makeup, repo: "hexpm", optional: false]}], "hexpm"},
+  "nimble_parsec": {:hex, :nimble_parsec, "0.5.0", "90e2eca3d0266e5c53f8fbe0079694740b9c91b6747f2b7e3c5d21966bba8300", [:mix], [], "hexpm"},
+}