Update HTTP documentation and bring back RFC entries

Closes #578.

Thibaut Courouble committed 9 years ago

Commit a64d8f31 parent 7e51d082 files · +95 −3Browse files

Unified · Split

2 files

lib/docs/filters/http/entries.rb +91 −3
lib/docs/scrapers/http.rb +4 −0

@@ -6,9 +6,9 @@ module Docs · 5 unmodified lines
6	6	name = at_css('h1').content
7	7	name.remove! %r{\A.+\:}
8	8	name.remove! %r{\A.+\-\-}
9		− rfc = slug.sub('rfc', 'RFC ')
	9	+ name = 'WebDAV' if name.include?('WebDAV')
10	10	"#{rfc}: #{name.strip}"
11		− elsif slug.start_with?('Status')
	11	+ elsif slug.start_with?('Status/')
12	12	at_css('code').content
13	13	else
14	14	name = super
@@ -22,7 +22,7 @@ module Docs · 7 unmodified lines
22	22	end
23	23
24	24	def get_type
25		− return 'RFC' if current_url.host == 'tools.ietf.org'
	25	+ return name if current_url.host == 'tools.ietf.org'
26	26
27	27	if slug.start_with?('Headers/Content-Security-Policy')
28	28	'CSP'
@@ -38,6 +38,94 @@ module Docs · 9 unmodified lines
38	38	'Guides'
39	39	end
40	40	end
	41	+
	42	+ def rfc
	43	+ slug.sub('rfc', 'RFC ')
	44	+ end
	45	+
	46	+ SECTIONS = {
	47	+ 'rfc2616' => [
	48	+ [3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 15],
	49	+ [14],
	50	+ []
	51	+ ],
	52	+ 'rfc4918' => [
	53	+ [],
	54	+ [11],
	55	+ []
	56	+ ],
	57	+ 'rfc7230' => [
	58	+ (2..9).to_a,
	59	+ [],
	60	+ []
	61	+ ],
	62	+ 'rfc7231' => [
	63	+ [3, 8, 9],
	64	+ [],
	65	+ [4, 5, 6, 7]
	66	+ ],
	67	+ 'rfc7232' => [
	68	+ [5, 6, 7, 8],
	69	+ [2, 3, 4],
	70	+ []
	71	+ ],
	72	+ 'rfc7233' => [
	73	+ [5, 6],
	74	+ [2, 3, 4],
	75	+ []
	76	+ ],
	77	+ 'rfc7234' => [
	78	+ [3, 6, 7, 8],
	79	+ [4, 5],
	80	+ []
	81	+ ],
	82	+ 'rfc7235' => [
	83	+ [2, 5, 6],
	84	+ [3, 4],
	85	+ []
	86	+ ]
	87	+ }
	88	+
	89	+ LEVEL_1 = /\A(\d+)\z/
	90	+ LEVEL_2 = /\A(\d+)\.\d+\z/
	91	+ LEVEL_3 = /\A(\d+)\.\d+\.\d+\z/
	92	+
	93	+ def additional_entries
	94	+ return [] unless current_url.host == 'tools.ietf.org'
	95	+ type = nil
	96	+
	97	+ css('a[href^="#section-"]').each_with_object([]) do \|node, entries\|
	98	+ id = node['href'].remove('#')
	99	+ break entries if entries.any? { \|e\| e[1] == id }
	100	+
	101	+ content = node.next.content.strip
	102	+ content.remove! %r{\s\.+\d\z}
	103	+ content.remove! %r{\A[\.\s]+}
	104	+
	105	+ name = "#{content} (#{rfc})"
	106	+ number = node.content.strip
	107	+
	108	+ if number =~ LEVEL_1
	109	+ if SECTIONS[slug][0].include?($1.to_i)
	110	+ entries << [name, id, self.name]
	111	+ end
	112	+
	113	+ type = content.sub(/\ Definitions\z/, 's')
	114	+ if type.include?('Header Fields')
	115	+ type = 'Headers'
	116	+ elsif type.include?('Status Codes')
	117	+ type = 'Status'
	118	+ elsif type.include?('Methods')
	119	+ type = 'Methods'
	120	+ else
	121	+ type = self.name
	122	+ end
	123	+ elsif (number =~ LEVEL_2 && SECTIONS[slug][1].include?($1.to_i)) \|\|
	124	+ (number =~ LEVEL_3 && SECTIONS[slug][2].include?($1.to_i))
	125	+ entries << [name, id, (name =~ /\A\d\d\d/ ? 'Status' : type )]
	126	+ end
	127	+ end
	128	+ end
41	129	end
42	130	end
43	131	end

lib/docs/scrapers/http.rb+4−0

@@ -17,6 +17,10 @@ module Docs · 16 unmodified lines
17	17	options[:skip_links] = ->(filter) {
18	18	filter.current_url.host == 'tools.ietf.org' ? true : false
19	19	}
	20	+ options[:fix_urls] = ->(url) {
	21	+ url.sub! %r{(Status/\d\d\d)_[A-Z].+}, '\1'
	22	+ url
	23	+ }
20	24	options[:attribution] = ->(filter) {
21	25	if filter.current_url.host == 'tools.ietf.org'
22	26	"© document authors. All rights reserved."