File: search_data.ex

package info (click to toggle)
elixir-ex-doc 0.35.1%2Bdfsg-4
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 1,784 kB
  • sloc: javascript: 2,848; makefile: 15; xml: 12; sh: 5
file content (159 lines) | stat: -rw-r--r-- 3,741 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
defmodule ExDoc.Formatter.HTML.SearchData do
  @moduledoc false
  alias ExDoc.Utils

  def create(nodes, extras, proglang) do
    items = Enum.flat_map(nodes, &module/1) ++ Enum.flat_map(extras, &extra/1)

    data = %{
      items: items,
      content_type: "text/markdown",
      proglang: proglang,
      producer: %{
        name: "ex_doc",
        version: to_string(Application.spec(:ex_doc)[:vsn])
      }
    }

    ["searchData=" | ExDoc.Utils.to_json(data)]
  end

  defp extra(map) do
    {intro, sections} = extract_sections_from_markdown(map.source)

    intro_json_item =
      encode(
        "#{map.id}.html",
        map.title,
        :extras,
        intro
      )

    section_json_items =
      for {header, body} <- sections do
        encode(
          "#{map.id}.html##{Utils.text_to_id(header)}",
          header <> " - #{map.title}",
          :extras,
          body
        )
      end

    [intro_json_item | section_json_items]
  end

  defp module(%ExDoc.ModuleNode{} = node) do
    {intro, sections} = extract_sections(node.doc_format, node)

    module =
      encode(
        "#{node.id}.html",
        node.title,
        node.type,
        intro
      )

    module_sections =
      for {header, body} <- sections do
        encode(
          "#{node.id}.html#module-#{Utils.text_to_id(header)}",
          header <> " - #{node.title}",
          node.type,
          body
        )
      end

    functions = Enum.flat_map(node.docs, &node_child(&1, node))
    types = Enum.flat_map(node.typespecs, &node_child(&1, node))
    [module] ++ module_sections ++ functions ++ types
  end

  defp node_child(node, module_node) do
    {intro, sections} = extract_sections(module_node.doc_format, node)

    child =
      encode(
        "#{module_node.id}.html##{node.id}",
        "#{module_node.id}.#{node.name}/#{node.arity}",
        node.type,
        intro
      )

    child_sections =
      for {header, body} <- sections do
        encode(
          "#{module_node.id}.html##{node.id}-#{Utils.text_to_id(header)}",
          header <> " - #{module_node.id}.#{node.name}/#{node.arity}",
          node.type,
          body
        )
      end

    [child] ++ child_sections
  end

  defp encode(ref, title, type, doc) do
    %{
      ref: URI.encode(ref),
      title: title,
      type: type,
      doc: doc
    }
  end

  defp extract_sections("text/markdown", %{source_doc: %{"en" => doc}}) do
    extract_sections_from_markdown(doc)
  end

  defp extract_sections("application/erlang+html", %{rendered_doc: nil}) do
    {nil, []}
  end

  defp extract_sections("application/erlang+html", %{rendered_doc: doc}) do
    {clean_html(doc), []}
  end

  defp extract_sections(_format, _doc) do
    {"", []}
  end

  defp extract_sections_from_markdown(string) do
    [intro | sections] =
      Regex.split(~r/(?<!#)###? (?<header>\b.+)/, string, include_captures: true)

    sections =
      for [header, section] <- Enum.chunk_every(sections, 2) do
        header = String.trim_leading(header, "#")

        section =
          section
          |> ExDoc.Utils.strip_tags(" ")
          |> drop_ignorable_codeblocks()
          |> String.trim()

        {clean_markdown(header), section}
      end

    {clean_markdown(intro), sections}
  end

  defp clean_markdown(doc) do
    doc
    |> ExDoc.Utils.strip_tags(" ")
    |> String.trim()
  end

  defp clean_html(doc) do
    doc
    |> ExDoc.Utils.strip_tags(" ")
    |> String.replace(~r/\s+/, " ")
    |> String.trim()
  end

  @ignored_codeblocks ~w[vega-lite]

  defp drop_ignorable_codeblocks(section) do
    block_names = Enum.join(@ignored_codeblocks, "|")
    String.replace(section, ~r/^```(?:#{block_names})\n(?:[\s\S]*?)```$/m, "")
  end
end