augusts_fancy_blog_post_parser 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/augusts_fancy_blog_post_parser.gemspec +13 -0
- data/lib/augusts_fancy_blog_post_parser.rb +124 -0
- metadata +72 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 99d7da55d26f476768aa953faba2cfbd46df0db9
|
4
|
+
data.tar.gz: e240d0f31fc833d20c9711294fe66291d989eebd
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 389ec05498d9c781fc24dfeaa4afced9a8a20d2df0eb0c46f13bca4f5cbd6df6b669193d6047bdad20bc927b9e3c3a7a66b9aba3ca0d92ef66730359a1f331c1
|
7
|
+
data.tar.gz: a5a18957a04d413e1481a00f89bdcd1572833be1630e40d98e643cd3ca3b1caf6f8dc1529fc6ab3ed73334e208f0c031cd412098b98f69becd8432178dbf1a77
|
@@ -0,0 +1,13 @@
|
|
1
|
+
Gem::Specification.new do |s|
|
2
|
+
s.name = "augusts_fancy_blog_post_parser"
|
3
|
+
s.version = "0.1.0"
|
4
|
+
s.authors = ["August Lilleaas"]
|
5
|
+
s.email = "august@augustl.com"
|
6
|
+
s.summary = "August's fancy blog post parser"
|
7
|
+
s.add_runtime_dependency "nokogiri", "~> 1.5.0"
|
8
|
+
s.add_runtime_dependency "parallel", "~> 0.7.0"
|
9
|
+
s.files = [
|
10
|
+
"lib/augusts_fancy_blog_post_parser.rb",
|
11
|
+
"augusts_fancy_blog_post_parser.gemspec"
|
12
|
+
]
|
13
|
+
end
|
@@ -0,0 +1,124 @@
|
|
1
|
+
require "nokogiri"
|
2
|
+
require "parallel"
|
3
|
+
require "open3"
|
4
|
+
|
5
|
+
class AugustsFancyBlogPostParser
|
6
|
+
attr_reader :url
|
7
|
+
attr_reader :body
|
8
|
+
|
9
|
+
def self.escape_html(html)
|
10
|
+
html
|
11
|
+
.gsub(/&(?!\w+;)/, '&')
|
12
|
+
.gsub(/</, '<')
|
13
|
+
.gsub(/>/, '>')
|
14
|
+
.gsub(/"/, '"')
|
15
|
+
end
|
16
|
+
|
17
|
+
def self.parse_html_attrs(attrs)
|
18
|
+
if attrs.blank?
|
19
|
+
return {}
|
20
|
+
else
|
21
|
+
Nokogiri::HTML("<div#{attrs}></div>").css("div")[0].attributes.inject({}) do |prev, curr|
|
22
|
+
key = curr[0]
|
23
|
+
value = curr[1]
|
24
|
+
prev[key] = value.value
|
25
|
+
prev
|
26
|
+
end
|
27
|
+
end
|
28
|
+
end
|
29
|
+
|
30
|
+
def self.format_code(code, lang)
|
31
|
+
if lang
|
32
|
+
formatted = nil
|
33
|
+
Open3.popen3("pygmentize", "-l", lang, "-f", "html", "-P", "nowrap=true") do |stdin, stdout, stderr, wait_thr|
|
34
|
+
stdin.write(code)
|
35
|
+
stdin.close_write
|
36
|
+
|
37
|
+
lines = []
|
38
|
+
until (line = stdout.gets).nil?
|
39
|
+
lines.push(line)
|
40
|
+
end
|
41
|
+
|
42
|
+
formatted = lines.join("").rstrip
|
43
|
+
end
|
44
|
+
|
45
|
+
"<code class=\"highlight\">#{formatted}</code>"
|
46
|
+
else
|
47
|
+
"<code>" + escape_html(code) + "</code>"
|
48
|
+
end
|
49
|
+
end
|
50
|
+
|
51
|
+
def self.separate_on(str, re, result = [])
|
52
|
+
match_data = str.match(re)
|
53
|
+
if match_data
|
54
|
+
result.push(match_data.pre_match)
|
55
|
+
result.push(match_data)
|
56
|
+
separate_on(match_data.post_match, re, result)
|
57
|
+
else
|
58
|
+
result.push(str)
|
59
|
+
result
|
60
|
+
end
|
61
|
+
end
|
62
|
+
|
63
|
+
def initialize(cwd, path)
|
64
|
+
@path = path
|
65
|
+
@cwd = cwd
|
66
|
+
@url = "/" + @path[0...-(File.extname(@path).length)]
|
67
|
+
reload!
|
68
|
+
end
|
69
|
+
|
70
|
+
def self.parse_body(body)
|
71
|
+
chunks = separate_on(body, /\<code(.*?)\>(.*?)\<\/code\>/m)
|
72
|
+
Parallel.map(chunks, :in_threads => chunks.length) do |chunk|
|
73
|
+
case chunk
|
74
|
+
when String
|
75
|
+
chunk
|
76
|
+
when MatchData
|
77
|
+
attrs = parse_html_attrs(chunk[1])
|
78
|
+
code = chunk[2]
|
79
|
+
format_code(code, attrs["data-lang"])
|
80
|
+
else
|
81
|
+
raise ArgumentError.new("Unexpected chunk #{chunk.class}.")
|
82
|
+
end
|
83
|
+
end.join("")
|
84
|
+
end
|
85
|
+
|
86
|
+
def reload!
|
87
|
+
html = File.read(@cwd + "/" + @path)
|
88
|
+
|
89
|
+
@headers = {}
|
90
|
+
num_header_chars = 0
|
91
|
+
|
92
|
+
html.each_line.each do |line|
|
93
|
+
if line =~ /[a-z]+\:./
|
94
|
+
key, _, value = *line.partition(":")
|
95
|
+
@headers[key] = value.chomp
|
96
|
+
num_header_chars += line.length
|
97
|
+
else
|
98
|
+
break
|
99
|
+
end
|
100
|
+
end
|
101
|
+
|
102
|
+
@body = self.class.parse_body(html[num_header_chars..-1])
|
103
|
+
end
|
104
|
+
|
105
|
+
def id
|
106
|
+
url.gsub("/", ":")
|
107
|
+
end
|
108
|
+
|
109
|
+
def title
|
110
|
+
@headers["title"].strip
|
111
|
+
end
|
112
|
+
|
113
|
+
def timestamp
|
114
|
+
Time.parse(@headers["date"])
|
115
|
+
end
|
116
|
+
|
117
|
+
def html_date
|
118
|
+
timestamp.strftime("%Y-%m-%d")
|
119
|
+
end
|
120
|
+
|
121
|
+
def display_date
|
122
|
+
timestamp.strftime("%B %d, %Y")
|
123
|
+
end
|
124
|
+
end
|
metadata
ADDED
@@ -0,0 +1,72 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: augusts_fancy_blog_post_parser
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- August Lilleaas
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2013-12-30 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: nokogiri
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ~>
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: 1.5.0
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ~>
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: 1.5.0
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: parallel
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ~>
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: 0.7.0
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ~>
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: 0.7.0
|
41
|
+
description:
|
42
|
+
email: august@augustl.com
|
43
|
+
executables: []
|
44
|
+
extensions: []
|
45
|
+
extra_rdoc_files: []
|
46
|
+
files:
|
47
|
+
- lib/augusts_fancy_blog_post_parser.rb
|
48
|
+
- augusts_fancy_blog_post_parser.gemspec
|
49
|
+
homepage:
|
50
|
+
licenses: []
|
51
|
+
metadata: {}
|
52
|
+
post_install_message:
|
53
|
+
rdoc_options: []
|
54
|
+
require_paths:
|
55
|
+
- lib
|
56
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
57
|
+
requirements:
|
58
|
+
- - '>='
|
59
|
+
- !ruby/object:Gem::Version
|
60
|
+
version: '0'
|
61
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
62
|
+
requirements:
|
63
|
+
- - '>='
|
64
|
+
- !ruby/object:Gem::Version
|
65
|
+
version: '0'
|
66
|
+
requirements: []
|
67
|
+
rubyforge_project:
|
68
|
+
rubygems_version: 2.0.14
|
69
|
+
signing_key:
|
70
|
+
specification_version: 4
|
71
|
+
summary: August's fancy blog post parser
|
72
|
+
test_files: []
|