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
|
# frozen_string_literal: true
module JekyllTitlesFromHeadings
class Generator < Jekyll::Generator
attr_accessor :site
TITLE_REGEX =
%r!
\A\s* # Beginning and whitespace
(?: # either
\#{1,3}\s+(.*)(?:\s+\#{1,3})? # atx-style header
| # or
(.*)\r?\n[-=]+\s* # Setex-style header
)$ # end of line
!x.freeze
CONVERTER_CLASS = Jekyll::Converters::Markdown
STRIP_MARKUP_FILTERS = [:markdownify, :strip_html, :normalize_whitespace].freeze
# Regex to strip extra markup still present after markdownify
# (footnotes at the moment).
EXTRA_MARKUP_REGEX = %r!\[\^[^\]]*\]!.freeze
CONFIG_KEY = "titles_from_headings"
ENABLED_KEY = "enabled"
STRIP_TITLE_KEY = "strip_title"
COLLECTIONS_KEY = "collections"
safe true
priority :lowest
def initialize(site)
@site = site
end
def generate(site)
@site = site
return if disabled?
documents = site.pages
documents = site.pages + site.docs_to_write if collections?
documents.each do |document|
next unless should_add_title?(document)
next if document.is_a?(Jekyll::StaticFile)
document.data["title"] = title_for(document)
strip_title!(document) if strip_title?(document)
end
end
def should_add_title?(document)
markdown?(document) && !title?(document)
end
def title?(document)
!inferred_title?(document) && !document.data["title"].nil?
end
def markdown?(document)
markdown_converter.matches(document.extname)
end
def markdown_converter
@markdown_converter ||= site.find_converter_instance(CONVERTER_CLASS)
end
def title_for(document)
return document.data["title"] if title?(document)
matches = document.content.to_s.match(TITLE_REGEX)
return strip_markup(matches[1] || matches[2]) if matches
document.data["title"] # If we cant match a title, we use the inferred one.
rescue ArgumentError => e
raise e unless e.to_s.start_with?("invalid byte sequence in UTF-8")
end
private
def strip_markup(string)
STRIP_MARKUP_FILTERS.reduce(string) do |memo, method|
filters.public_send(method, memo)
end.gsub(EXTRA_MARKUP_REGEX, "")
end
def option(key)
site.config[CONFIG_KEY] && site.config[CONFIG_KEY][key]
end
def disabled?
option(ENABLED_KEY) == false
end
def strip_title?(document)
if document.data.key?(STRIP_TITLE_KEY)
document.data[STRIP_TITLE_KEY] == true
else
option(STRIP_TITLE_KEY) == true
end
end
def strip_title_excerpt?(document)
document.is_a?(Jekyll::Document) &&
document.collection.label == "posts" &&
document.generate_excerpt?
end
def collections?
option(COLLECTIONS_KEY) == true
end
# Documents (posts and collection items) have their title inferred from the filename.
# We want to override these titles, because they were not excplicitly set.
def inferred_title?(document)
document.is_a?(Jekyll::Document)
end
def strip_title!(document)
if document.content
document.content = document.content.gsub(TITLE_REGEX, "").strip
strip_title_excerpt!(document) if strip_title_excerpt?(document)
end
end
def strip_title_excerpt!(document)
document.data["excerpt"] = Jekyll::Excerpt.new(document)
end
def filters
@filters ||= JekyllTitlesFromHeadings::Filters.new(site)
end
end
end
|
