Packages
html_to_markdown
2.14.0
3.9.0
3.8.3
3.8.2
3.8.1
3.8.0
3.8.0-rc.2
3.8.0-rc.1
3.7.2
3.7.1
3.7.0
3.6.21
3.6.20
3.6.19
3.6.18
3.6.17
3.6.16
3.6.15
3.6.14
3.6.13
3.6.11
3.6.10
3.6.9
3.6.8
3.6.3
3.6.1
3.6.0
3.6.0-rc.25
3.6.0-rc.23
3.6.0-rc.22
3.6.0-rc.21
3.6.0-rc.20
3.6.0-rc.17
3.6.0-rc.16
3.6.0-rc.14
3.6.0-rc.13
3.6.0-rc.12
3.6.0-rc.11
3.6.0-rc.10
3.6.0-rc.9
3.6.0-rc.7
3.6.0-rc.3
3.6.0-rc.2
3.6.0-rc.1
3.5.7
3.5.5
3.5.3
3.5.2
3.5.1
3.5.0
3.5.0-rc.1
3.4.0
3.4.0-rc.45
3.4.0-rc.44
3.4.0-rc.42
3.4.0-rc.41
3.4.0-rc.40
3.4.0-rc.25
3.4.0-rc.24
3.4.0-rc.23
3.4.0-rc.21
3.4.0-rc.20
3.4.0-rc.18
3.4.0-rc.16
3.4.0-rc.15
3.4.0-rc.14
3.4.0-rc.13
3.4.0-rc.12
3.4.0-rc.11
3.4.0-rc.9
3.4.0-rc.8
3.4.0-rc.2
3.4.0-rc.1
3.3.2
3.2.4
3.2.2
3.2.1
3.2.0
3.1.0
3.0.2
3.0.1
3.0.0
2.30.0
2.29.0
2.28.6
2.28.5
2.28.4
2.28.3
2.28.2
2.28.1
2.28.0
2.27.3
2.27.2
2.27.1
2.27.0
2.26.3
2.26.2
2.26.1
2.25.1
2.25.0
2.24.6
2.24.5
2.24.4
2.24.3
2.24.1
2.23.4
2.23.3
2.23.2
2.23.1
2.23.0
2.22.5
2.22.2
2.22.1
2.22.0
2.21.1
2.20.0
2.19.8
2.19.7
2.19.6
2.19.5
2.19.4
2.19.3
2.19.2
2.19.1
2.19.0
2.18.0
2.16.1
2.16.0
2.15.0
2.14.11
2.14.10
2.14.9
2.14.8
2.14.7
2.14.6
2.14.3
2.14.2
2.14.1
2.14.0
2.13.0
2.12.1
2.12.0
2.11.4
2.11.3
2.11.1
2.10.1
2.9.2
2.9.1
2.9.0
2.8.3
High-performance HTML to Markdown converter
Current section
Files
Jump to
Current section
Files
lib/html_to_markdown.ex
defmodule HtmlToMarkdown do
@moduledoc """
High-level Elixir interface for the Rust html-to-markdown engine.
"""
alias HtmlToMarkdown.{
Error,
InlineImage,
InlineImageConfig,
InlineImageWarning,
Native,
Options
}
@type options_input :: Options.t() | map() | keyword() | nil
@type inline_config_input :: InlineImageConfig.t() | map() | keyword() | nil
@doc """
Convert HTML to Markdown.
The `options` argument accepts an `%HtmlToMarkdown.Options{}` struct,
a map/keyword list with option keys, or `nil` (defaults).
"""
@spec convert(String.t(), options_input()) :: {:ok, String.t()} | {:error, term()}
def convert(html, options \\ nil) when is_binary(html) do
options_map = normalize_options(options)
case call_convert(html, options_map) do
{:ok, markdown} -> {:ok, markdown}
{:error, reason} -> {:error, reason}
end
end
@doc """
Convert HTML to Markdown and raise on failure.
"""
@spec convert!(String.t(), options_input()) :: String.t()
def convert!(html, options \\ nil) do
case convert(html, options) do
{:ok, markdown} -> markdown
{:error, reason} -> raise Error, message: inspect(reason)
end
end
@doc """
Convert HTML using a reusable options handle.
"""
@spec convert_with_options(String.t(), reference()) :: {:ok, String.t()} | {:error, term()}
def convert_with_options(html, handle) when is_binary(html) do
Native.convert_with_handle(html, handle)
end
@doc """
Variant of `convert_with_options/2` that raises on failure.
"""
@spec convert_with_options!(String.t(), reference()) :: String.t()
def convert_with_options!(html, handle) do
case convert_with_options(html, handle) do
{:ok, markdown} -> markdown
{:error, reason} -> raise Error, message: inspect(reason)
end
end
@doc """
Convert HTML and collect inline image assets.
Returns `{:ok, markdown, inline_images, warnings}`.
"""
@spec convert_with_inline_images(String.t(), options_input(), inline_config_input()) ::
{:ok, String.t(), [InlineImage.t()], [InlineImageWarning.t()]}
| {:error, term()}
def convert_with_inline_images(html, options \\ nil, inline_config \\ nil)
when is_binary(html) do
options_map = normalize_options(options) || %{}
with {:ok, config_map} <- InlineImageConfig.to_map_result(inline_config),
{:ok, {markdown, images, warnings}} <-
Native.convert_with_inline_images(html, options_map, config_map) do
{:ok, markdown, Enum.map(images, &into_inline_image/1), Enum.map(warnings, &into_warning/1)}
else
{:error, reason} -> {:error, reason}
end
end
@doc """
Bang variant of `convert_with_inline_images/3`.
"""
@spec convert_with_inline_images!(String.t(), options_input(), inline_config_input()) ::
{String.t(), [InlineImage.t()], [InlineImageWarning.t()]}
def convert_with_inline_images!(html, options \\ nil, inline_config \\ nil) do
case convert_with_inline_images(html, options, inline_config) do
{:ok, markdown, images, warnings} -> {markdown, images, warnings}
{:error, reason} -> raise Error, message: inspect(reason)
end
end
@doc """
Create a reusable options handle (opaque reference).
The handle can be passed to `convert_with_options/2`.
"""
@spec options(options_input()) :: reference()
def options(opts \\ nil) do
opts_map = normalize_options(opts) || %{}
case Native.create_options_handle(opts_map) do
{:ok, handle} ->
handle
{:error, reason} ->
raise Error, message: inspect(reason)
end
end
defp call_convert(html, nil), do: Native.convert(html)
defp call_convert(html, options) when options == %{}, do: Native.convert(html)
defp call_convert(html, options), do: Native.convert_with_options_map(html, options)
defp normalize_options(nil), do: nil
defp normalize_options(options) do
options
|> Options.new()
|> Options.to_map()
end
defp into_inline_image(map) do
data = fetch(map, :data)
format = fetch(map, :format)
filename = fetch(map, :filename)
description = fetch(map, :description)
dimensions = normalize_dimensions(fetch(map, :dimensions))
source = normalize_source(fetch(map, :source))
attributes = fetch(map, :attributes) || %{}
%InlineImage{
data: data,
format: format,
filename: filename,
description: description,
dimensions: dimensions,
source: source,
attributes: attributes
}
end
defp into_warning(map) do
index = fetch(map, :index)
message = fetch(map, :message)
%InlineImageWarning{index: index, message: message}
end
defp fetch(map, key) when is_atom(key) do
Map.get(map, key) || Map.get(map, Atom.to_string(key))
end
defp normalize_source(value) when is_atom(value), do: Atom.to_string(value)
defp normalize_source(value) when is_binary(value), do: value
defp normalize_source(_), do: "img_data_uri"
defp normalize_dimensions({width, height}) when is_integer(width) and is_integer(height),
do: {width, height}
defp normalize_dimensions([width, height]) when is_integer(width) and is_integer(height),
do: {width, height}
defp normalize_dimensions(_), do: nil
end