mill 0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +37 -0
- data/Gemfile +6 -0
- data/LICENSE +21 -0
- data/README.md +4 -0
- data/Rakefile +1 -0
- data/TODO.txt +38 -0
- data/lib/mill.rb +336 -0
- data/lib/mill/file_types.rb +30 -0
- data/lib/mill/html_helpers.rb +166 -0
- data/lib/mill/navigator.rb +84 -0
- data/lib/mill/resource.rb +116 -0
- data/lib/mill/resources/feed.rb +63 -0
- data/lib/mill/resources/generic.rb +15 -0
- data/lib/mill/resources/image.rb +36 -0
- data/lib/mill/resources/redirect.rb +36 -0
- data/lib/mill/resources/robots.rb +25 -0
- data/lib/mill/resources/sitemap.rb +35 -0
- data/lib/mill/resources/text.rb +157 -0
- data/lib/mill/schemas/atom.xsd +244 -0
- data/lib/mill/schemas/sitemap.xsd +116 -0
- data/lib/mill/tasks.rake +31 -0
- data/lib/mill/version.rb +5 -0
- data/mill.gemspec +37 -0
- metadata +247 -0
@@ -0,0 +1,30 @@
|
|
1
|
+
class Mill
|
2
|
+
|
3
|
+
FileTypes = {
|
4
|
+
text: %w{
|
5
|
+
text/plain
|
6
|
+
text/html
|
7
|
+
},
|
8
|
+
image: %w{
|
9
|
+
image/gif
|
10
|
+
image/jpeg
|
11
|
+
image/png
|
12
|
+
image/tiff
|
13
|
+
image/vnd.microsoft.icon
|
14
|
+
image/x-icon
|
15
|
+
},
|
16
|
+
generic: %w{
|
17
|
+
text/css
|
18
|
+
application/font-sfnt
|
19
|
+
application/x-font-opentype
|
20
|
+
application/x-font-otf
|
21
|
+
application/x-font-truetype
|
22
|
+
application/x-font-ttf
|
23
|
+
application/javascript
|
24
|
+
application/x-javascript
|
25
|
+
text/javascript
|
26
|
+
application/pdf
|
27
|
+
},
|
28
|
+
}
|
29
|
+
|
30
|
+
end
|
@@ -0,0 +1,166 @@
|
|
1
|
+
module HTMLHelpers
|
2
|
+
|
3
|
+
class HTMLError < Exception; end
|
4
|
+
|
5
|
+
IgnoreErrors = %Q{
|
6
|
+
<table> lacks "summary" attribute
|
7
|
+
<img> lacks "alt" attribute
|
8
|
+
<form> proprietary attribute "novalidate"
|
9
|
+
<input> attribute "type" has invalid value "email"
|
10
|
+
<input> attribute "tabindex" has invalid value "-1"
|
11
|
+
}.split(/\n/).map(&:strip)
|
12
|
+
|
13
|
+
def html_document(&block)
|
14
|
+
builder = Nokogiri::HTML::Builder.new(encoding: 'utf-8') do |doc|
|
15
|
+
yield(doc)
|
16
|
+
end
|
17
|
+
builder.doc
|
18
|
+
end
|
19
|
+
|
20
|
+
def html_fragment(&block)
|
21
|
+
html = Nokogiri::HTML::DocumentFragment.parse('')
|
22
|
+
Nokogiri::HTML::Builder.with(html) do |html|
|
23
|
+
yield(html)
|
24
|
+
end
|
25
|
+
html
|
26
|
+
end
|
27
|
+
|
28
|
+
def parse_html(str)
|
29
|
+
html = Nokogiri::HTML::Document.parse(str) { |config| config.strict }
|
30
|
+
html.errors.each do |error|
|
31
|
+
next if error.message =~ /^Tag (.*?) invalid$/
|
32
|
+
raise HTMLError, "HTML error at line #{error.line}, column #{error.column}: #{error.message}"
|
33
|
+
end
|
34
|
+
html
|
35
|
+
end
|
36
|
+
|
37
|
+
def tidy_html(html, &block)
|
38
|
+
html_str = html.to_s
|
39
|
+
tidy = TidyFFI::Tidy.new(html_str, char_encoding: 'UTF8')
|
40
|
+
errors = parse_tidy_errors(tidy).reject do |error|
|
41
|
+
IgnoreErrors.include?(error[:error])
|
42
|
+
end
|
43
|
+
unless errors.empty?
|
44
|
+
full_error = StringIO.new('')
|
45
|
+
full_error.puts "invalid HTML:"
|
46
|
+
html_lines = html_str.split(/\n/)
|
47
|
+
errors.each do |error|
|
48
|
+
full_error.puts "\t#{error[:msg]}:"
|
49
|
+
html_lines.each_with_index do |html_line, i|
|
50
|
+
if i >= [0, error[:line] - 2].max && i <= [error[:line] + 2, html_lines.length].min
|
51
|
+
if i == error[:line]
|
52
|
+
output = [
|
53
|
+
error[:column] > 0 ? (html_line[0 .. error[:column] - 1]) : '',
|
54
|
+
Term::ANSIColor.negative,
|
55
|
+
html_line[error[:column]],
|
56
|
+
Term::ANSIColor.clear,
|
57
|
+
html_line[error[:column] + 1 .. -1],
|
58
|
+
]
|
59
|
+
else
|
60
|
+
output = [html_line]
|
61
|
+
end
|
62
|
+
full_error.puts "\t\t%3s: %s" % [i + 1, output.join]
|
63
|
+
end
|
64
|
+
end
|
65
|
+
if block_given?
|
66
|
+
yield(full_error.string)
|
67
|
+
else
|
68
|
+
STDERR.print(full_error.string)
|
69
|
+
end
|
70
|
+
raise HTMLError, "HTML error: #{error[:msg]}" if error[:type] == :error
|
71
|
+
end
|
72
|
+
end
|
73
|
+
end
|
74
|
+
|
75
|
+
def parse_tidy_errors(tidy)
|
76
|
+
return [] unless tidy.errors
|
77
|
+
tidy.errors.split(/\n/).map do |error_str|
|
78
|
+
error_str =~ /^line (\d+) column (\d+) - (.*?): (.*)$/ or raise "Can't parse error: #{error_str}"
|
79
|
+
{
|
80
|
+
msg: error_str,
|
81
|
+
line: $1.to_i - 1,
|
82
|
+
column: $2.to_i - 1,
|
83
|
+
type: $3.downcase.to_sym,
|
84
|
+
error: $4.strip,
|
85
|
+
}
|
86
|
+
end
|
87
|
+
end
|
88
|
+
|
89
|
+
def replace_element(html, xpath, &block)
|
90
|
+
html.xpath(xpath).each do |elem|
|
91
|
+
elem.replace(yield(elem))
|
92
|
+
end
|
93
|
+
end
|
94
|
+
|
95
|
+
def amazon_button(asin)
|
96
|
+
html_fragment do |html|
|
97
|
+
html.a(href: "http://www.amazon.com/dp/#{asin}") do
|
98
|
+
html.img(src: '/images/buy1._V46787834_.gif', alt: 'Buy from Amazon.com')
|
99
|
+
end
|
100
|
+
end
|
101
|
+
end
|
102
|
+
|
103
|
+
def paypal_button(id)
|
104
|
+
html_fragment do |html|
|
105
|
+
html.form(action: 'https://www.paypal.com/cgi-bin/webscr', method: 'post') do
|
106
|
+
html.input(
|
107
|
+
type: 'hidden',
|
108
|
+
name: 'cmd',
|
109
|
+
value: '_s-xclick')
|
110
|
+
html.input(
|
111
|
+
type: 'hidden',
|
112
|
+
name: 'hosted_button_id',
|
113
|
+
value: id)
|
114
|
+
html.input(
|
115
|
+
type: 'image',
|
116
|
+
src: 'https://www.paypalobjects.com/en_US/i/btn/btn_buynow_LG.gif',
|
117
|
+
name: 'submit',
|
118
|
+
alt: 'PayPal - The safer, easier way to pay online!')
|
119
|
+
html.img(
|
120
|
+
alt: '',
|
121
|
+
border: 0,
|
122
|
+
width: 1,
|
123
|
+
height: 1,
|
124
|
+
src: 'https://www.paypalobjects.com/en_US/i/scr/pixel.gif')
|
125
|
+
end
|
126
|
+
end
|
127
|
+
end
|
128
|
+
|
129
|
+
def google_analytics(tracker_id)
|
130
|
+
html_fragment do |html|
|
131
|
+
html.script(type: 'text/javascript') do
|
132
|
+
html << %Q{
|
133
|
+
var gaJsHost = (("https:" == document.location.protocol) ? "https://ssl." : "http://www.");
|
134
|
+
document.write(unescape("%3Cscript src='" + gaJsHost + "google-analytics.com/ga.js' type='text/javascript'%3E%3C/script%3E"));
|
135
|
+
}
|
136
|
+
end
|
137
|
+
html.script(type: 'text/javascript') do
|
138
|
+
html << %Q{
|
139
|
+
try {
|
140
|
+
var pageTracker = _gat._getTracker("#{tracker_id}");
|
141
|
+
pageTracker._trackPageview();
|
142
|
+
} catch(err) {}
|
143
|
+
}
|
144
|
+
end
|
145
|
+
end
|
146
|
+
end
|
147
|
+
|
148
|
+
class PreText < String
|
149
|
+
|
150
|
+
def to_html
|
151
|
+
html_fragment do |html|
|
152
|
+
html.pre(self)
|
153
|
+
end
|
154
|
+
end
|
155
|
+
|
156
|
+
end
|
157
|
+
|
158
|
+
class ::String
|
159
|
+
|
160
|
+
def to_html
|
161
|
+
Nokogiri::HTML::DocumentFragment.parse(RubyPants.new(self).to_html).to_html
|
162
|
+
end
|
163
|
+
|
164
|
+
end
|
165
|
+
|
166
|
+
end
|
@@ -0,0 +1,84 @@
|
|
1
|
+
class Mill
|
2
|
+
|
3
|
+
class Navigator
|
4
|
+
|
5
|
+
class Item
|
6
|
+
|
7
|
+
attr_accessor :uri
|
8
|
+
attr_accessor :title
|
9
|
+
|
10
|
+
def initialize(params={})
|
11
|
+
params.each { |k, v| send("#{k}=", v) }
|
12
|
+
end
|
13
|
+
|
14
|
+
def uri=(uri)
|
15
|
+
@uri = Addressable::URI.parse(uri)
|
16
|
+
end
|
17
|
+
|
18
|
+
end
|
19
|
+
|
20
|
+
attr_accessor :items
|
21
|
+
|
22
|
+
def initialize(params={})
|
23
|
+
@items = []
|
24
|
+
params.each { |k, v| send("#{k}=", v) }
|
25
|
+
end
|
26
|
+
|
27
|
+
def item_states_for_uri(uri, &block)
|
28
|
+
current_item = within_item = nil
|
29
|
+
if (item = @items.find { |item| item.uri.relative? && item.uri == uri })
|
30
|
+
current_item = item
|
31
|
+
else
|
32
|
+
within_item = @items.select do |item|
|
33
|
+
item.uri.relative? && uri.path.start_with?(item.uri.path)
|
34
|
+
end.sort_by do |item|
|
35
|
+
item.uri.path.count('/')
|
36
|
+
end.last
|
37
|
+
end
|
38
|
+
@items.each do |item|
|
39
|
+
if item == current_item
|
40
|
+
state = :current
|
41
|
+
elsif item == within_item
|
42
|
+
state = :within
|
43
|
+
else
|
44
|
+
state = :other
|
45
|
+
end
|
46
|
+
yield(item, state)
|
47
|
+
end
|
48
|
+
end
|
49
|
+
|
50
|
+
def first_item
|
51
|
+
@items.first
|
52
|
+
end
|
53
|
+
|
54
|
+
def last_item
|
55
|
+
@items.last
|
56
|
+
end
|
57
|
+
|
58
|
+
def previous_item(uri)
|
59
|
+
index = find_item_index_by_uri(uri)
|
60
|
+
if index && index > 0
|
61
|
+
@items[index - 1]
|
62
|
+
else
|
63
|
+
nil
|
64
|
+
end
|
65
|
+
end
|
66
|
+
|
67
|
+
def next_item(uri)
|
68
|
+
index = find_item_index_by_uri(uri)
|
69
|
+
if index && index < @items.length - 1
|
70
|
+
@items[index + 1]
|
71
|
+
else
|
72
|
+
nil
|
73
|
+
end
|
74
|
+
end
|
75
|
+
|
76
|
+
def find_item_index_by_uri(uri)
|
77
|
+
if (item = @items.find { |item| item.uri == uri })
|
78
|
+
@items.index(item)
|
79
|
+
end
|
80
|
+
end
|
81
|
+
|
82
|
+
end
|
83
|
+
|
84
|
+
end
|
@@ -0,0 +1,116 @@
|
|
1
|
+
class Mill
|
2
|
+
|
3
|
+
class Resource
|
4
|
+
|
5
|
+
attr_accessor :input_file
|
6
|
+
attr_accessor :output_file
|
7
|
+
attr_accessor :date
|
8
|
+
attr_accessor :public
|
9
|
+
attr_accessor :content
|
10
|
+
attr_accessor :mill
|
11
|
+
|
12
|
+
def self.type
|
13
|
+
# implemented by subclass
|
14
|
+
end
|
15
|
+
|
16
|
+
def initialize(params={})
|
17
|
+
params.each { |k, v| send("#{k}=", v) }
|
18
|
+
end
|
19
|
+
|
20
|
+
def input_file=(p)
|
21
|
+
@input_file = Path.new(p)
|
22
|
+
end
|
23
|
+
|
24
|
+
def output_file=(p)
|
25
|
+
@output_file = Path.new(p)
|
26
|
+
end
|
27
|
+
|
28
|
+
def date=(x)
|
29
|
+
@date = case x
|
30
|
+
when String
|
31
|
+
DateTime.parse(x)
|
32
|
+
when Time
|
33
|
+
DateTime.parse(x.to_s)
|
34
|
+
when Date, DateTime
|
35
|
+
x
|
36
|
+
else
|
37
|
+
raise "Can't assign date: #{x.inspect}"
|
38
|
+
end
|
39
|
+
end
|
40
|
+
|
41
|
+
def public=(x)
|
42
|
+
@public = case x
|
43
|
+
when 'false', FalseClass
|
44
|
+
false
|
45
|
+
when 'true', TrueClass
|
46
|
+
true
|
47
|
+
else
|
48
|
+
raise "Can't assign public: #{x.inspect}"
|
49
|
+
end
|
50
|
+
end
|
51
|
+
|
52
|
+
def uri
|
53
|
+
raise "#{@input_file}: No output file defined for #{self.class}" unless @output_file
|
54
|
+
path = '/' + @output_file.relative_to(@mill.output_dir).to_s
|
55
|
+
path.sub!(%r{/index\.html$}, '/')
|
56
|
+
path.sub!(%r{\.html$}, '') if @mill.shorten_uris
|
57
|
+
Addressable::URI.parse(path)
|
58
|
+
end
|
59
|
+
|
60
|
+
def absolute_uri
|
61
|
+
@mill.site_uri + uri
|
62
|
+
end
|
63
|
+
|
64
|
+
def tag_uri
|
65
|
+
@mill.tag_uri + uri
|
66
|
+
end
|
67
|
+
|
68
|
+
def change_frequency
|
69
|
+
:weekly
|
70
|
+
end
|
71
|
+
|
72
|
+
def final_content
|
73
|
+
@content
|
74
|
+
end
|
75
|
+
|
76
|
+
def load
|
77
|
+
raise "#{uri} (#{self.class}): no content" unless @input_file || @content
|
78
|
+
self.date ||= @input_file ? @input_file.mtime : DateTime.now
|
79
|
+
@mill.update_resource(self)
|
80
|
+
end
|
81
|
+
|
82
|
+
def build
|
83
|
+
@output_file.dirname.mkpath
|
84
|
+
if (c = final_content)
|
85
|
+
# ;;warn "#{uri}: writing #{@input_file} to #{@output_file}"
|
86
|
+
@output_file.write(c.to_s)
|
87
|
+
@output_file.utime(@date.to_time, @date.to_time)
|
88
|
+
elsif @input_file
|
89
|
+
# ;;warn "#{uri}: copying #{@input_file} to #{@output_file}"
|
90
|
+
@input_file.copy(@output_file)
|
91
|
+
else
|
92
|
+
raise "Can't build resource without content or input file: #{uri}"
|
93
|
+
end
|
94
|
+
validate
|
95
|
+
end
|
96
|
+
|
97
|
+
def validate
|
98
|
+
if (schema = @mill.schema_for_type(self.class.type))
|
99
|
+
validate_xml(schema)
|
100
|
+
end
|
101
|
+
end
|
102
|
+
|
103
|
+
def validate_xml(schema)
|
104
|
+
doc = Nokogiri::XML::Document.parse(@output_file.open)
|
105
|
+
errors = doc.errors + schema.validate(doc)
|
106
|
+
unless errors.empty?
|
107
|
+
errors.each do |error|
|
108
|
+
warn "[#{error.file}:#{error.line}:#{error.column}] #{error}"
|
109
|
+
end
|
110
|
+
raise "#{uri}: Validation failed"
|
111
|
+
end
|
112
|
+
end
|
113
|
+
|
114
|
+
end
|
115
|
+
|
116
|
+
end
|
@@ -0,0 +1,63 @@
|
|
1
|
+
# see http://www.sitemaps.org/protocol.php
|
2
|
+
|
3
|
+
class Mill
|
4
|
+
|
5
|
+
class Resource
|
6
|
+
|
7
|
+
class Feed < Resource
|
8
|
+
|
9
|
+
include HTMLHelpers
|
10
|
+
|
11
|
+
def self.type
|
12
|
+
:feed
|
13
|
+
end
|
14
|
+
|
15
|
+
def load
|
16
|
+
resources = @mill.public_resources.sort_by(&:date)
|
17
|
+
builder = Nokogiri::XML::Builder.new do |xml|
|
18
|
+
xml.feed(xmlns: 'http://www.w3.org/2005/Atom') do
|
19
|
+
xml.id(@mill.tag_uri)
|
20
|
+
xml.generator(*@mill.feed_generator)
|
21
|
+
xml.title(@mill.site_title)
|
22
|
+
xml.link(rel: 'alternate', type: 'text/html', href: @mill.home_resource.uri)
|
23
|
+
xml.link(rel: 'self', type: 'application/atom+xml', href: uri)
|
24
|
+
xml.author do
|
25
|
+
xml.name(@mill.feed_author_name)
|
26
|
+
xml.uri(@mill.feed_author_uri)
|
27
|
+
xml.email(@mill.feed_author_email)
|
28
|
+
end
|
29
|
+
xml.updated(resources.last.date.iso8601)
|
30
|
+
resources.each do |resource|
|
31
|
+
xml.entry do
|
32
|
+
xml.title(resource.title) if resource.title
|
33
|
+
xml.link(rel: 'alternate', href: resource.uri)
|
34
|
+
xml.id(resource.tag_uri)
|
35
|
+
xml.updated(resource.date.iso8601)
|
36
|
+
xml.published(resource.date.iso8601)
|
37
|
+
if (resource.respond_to?(:feed_summary))
|
38
|
+
type, data = resource.feed_summary
|
39
|
+
xml.summary(type: type) { xml.cdata(data) } if type && data
|
40
|
+
end
|
41
|
+
if (resource.respond_to?(:feed_content))
|
42
|
+
type, data = resource.feed_content
|
43
|
+
xml.content(type: type) { xml.cdata(data) }
|
44
|
+
end
|
45
|
+
end
|
46
|
+
end
|
47
|
+
end
|
48
|
+
end
|
49
|
+
@content = builder.doc
|
50
|
+
super
|
51
|
+
end
|
52
|
+
|
53
|
+
def link_html
|
54
|
+
html_fragment do |html|
|
55
|
+
html.link(href: uri, rel: 'alternate', type: 'application/atom+xml')
|
56
|
+
end
|
57
|
+
end
|
58
|
+
|
59
|
+
end
|
60
|
+
|
61
|
+
end
|
62
|
+
|
63
|
+
end
|