zsff 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- data/History.txt +4 -0
- data/Manifest.txt +6 -0
- data/README.txt +52 -0
- data/Rakefile +18 -0
- data/lib/zsff.rb +112 -0
- data/test/test_zsff.rb +113 -0
- metadata +69 -0
data/History.txt
ADDED
data/Manifest.txt
ADDED
data/README.txt
ADDED
@@ -0,0 +1,52 @@
|
|
1
|
+
zsff
|
2
|
+
by Erik Peterson
|
3
|
+
http://subwindow.com/zsff
|
4
|
+
|
5
|
+
== DESCRIPTION:
|
6
|
+
|
7
|
+
A parser/validator for ZSFF feeds.
|
8
|
+
|
9
|
+
== FEATURES/PROBLEMS:
|
10
|
+
|
11
|
+
Right now, only one function: parse. This does the validation and parsing all in one step. This is intended to be used by any reader (who would take care of what links have been read, etc).
|
12
|
+
|
13
|
+
== SYNOPSIS:
|
14
|
+
|
15
|
+
results = Zsff.parse(url)
|
16
|
+
results[:errors] #Any errors encountered while parsing
|
17
|
+
results[:warnings] #Any warnings encountered while parsing
|
18
|
+
results[:attrs] #A hash for the author, title, etc information from the feed
|
19
|
+
results[:links] #List of links in the feed
|
20
|
+
|
21
|
+
== REQUIREMENTS:
|
22
|
+
|
23
|
+
None
|
24
|
+
|
25
|
+
== INSTALL:
|
26
|
+
|
27
|
+
sudo gem install, anything else
|
28
|
+
|
29
|
+
== LICENSE:
|
30
|
+
|
31
|
+
(The MIT License)
|
32
|
+
|
33
|
+
Copyright (c) 2008 Erik Peterson
|
34
|
+
|
35
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
36
|
+
a copy of this software and associated documentation files (the
|
37
|
+
'Software'), to deal in the Software without restriction, including
|
38
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
39
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
40
|
+
permit persons to whom the Software is furnished to do so, subject to
|
41
|
+
the following conditions:
|
42
|
+
|
43
|
+
The above copyright notice and this permission notice shall be
|
44
|
+
included in all copies or substantial portions of the Software.
|
45
|
+
|
46
|
+
THE SOFTWARE IS PROVIDED 'AS IS', WITHOUT WARRANTY OF ANY KIND,
|
47
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
48
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
|
49
|
+
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
|
50
|
+
CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
|
51
|
+
TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
|
52
|
+
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/Rakefile
ADDED
@@ -0,0 +1,18 @@
|
|
1
|
+
# -*- ruby -*-
|
2
|
+
|
3
|
+
require 'rubygems'
|
4
|
+
require 'hoe'
|
5
|
+
require './lib/zsff.rb'
|
6
|
+
|
7
|
+
Hoe.new('zsff', Zsff::VERSION) do |p|
|
8
|
+
p.rubyforge_name = 'zsff'
|
9
|
+
p.author = 'Erik Peterson'
|
10
|
+
p.email = 'erik@subwindow.com'
|
11
|
+
p.summary = 'A parser/validator for ZSFF feeds'
|
12
|
+
p.description = p.paragraphs_of('README.txt', 2..5).join("\n\n")
|
13
|
+
p.url = p.paragraphs_of('README.txt', 0).first.split(/\n/)[1..-1]
|
14
|
+
p.changes = p.paragraphs_of('History.txt', 0..1).join("\n\n")
|
15
|
+
p.remote_rdoc_dir = ''
|
16
|
+
end
|
17
|
+
|
18
|
+
# vim: syntax=Ruby
|
data/lib/zsff.rb
ADDED
@@ -0,0 +1,112 @@
|
|
1
|
+
# Author:: Erik Peterson (mailto:erik@subwindow.com)
|
2
|
+
# Copyright:: Copyright (c) 2008 Erik Peterson
|
3
|
+
# License:: MIT
|
4
|
+
|
5
|
+
# This class parses and validates a Zsff feed by URL or a raw feed string
|
6
|
+
|
7
|
+
require 'net/http'
|
8
|
+
require 'open-uri'
|
9
|
+
class Zsff
|
10
|
+
VERSION = '1.0.0'
|
11
|
+
attr_accessor :url
|
12
|
+
attr_accessor :contents
|
13
|
+
attr_accessor :errors
|
14
|
+
attr_accessor :warnings
|
15
|
+
attr_accessor :version
|
16
|
+
attr_accessor :author
|
17
|
+
attr_accessor :title
|
18
|
+
attr_accessor :site
|
19
|
+
attr_accessor :subtitle
|
20
|
+
attr_accessor :copyright
|
21
|
+
attr_accessor :content_type
|
22
|
+
attr_accessor :links
|
23
|
+
|
24
|
+
def initialize(attributes = nil)
|
25
|
+
self.attributes = attributes unless attributes.nil?
|
26
|
+
@errors = []
|
27
|
+
@warnings = []
|
28
|
+
@links = []
|
29
|
+
end
|
30
|
+
|
31
|
+
def self.parse_url(url)
|
32
|
+
parser = self.new(:url => url)
|
33
|
+
parser.parse
|
34
|
+
return parser
|
35
|
+
end
|
36
|
+
|
37
|
+
def self.parse_contents(contents)
|
38
|
+
parser = self.new(:contents => contents)
|
39
|
+
parser.parse
|
40
|
+
return parser
|
41
|
+
end
|
42
|
+
|
43
|
+
def attributes=(attributes)
|
44
|
+
attributes.each do |k, v|
|
45
|
+
send(k.to_s + "=", v)
|
46
|
+
end
|
47
|
+
end
|
48
|
+
|
49
|
+
def parse
|
50
|
+
if self.url
|
51
|
+
begin
|
52
|
+
uri = URI.parse(url)
|
53
|
+
@contents = Net::HTTP.get(uri)
|
54
|
+
rescue
|
55
|
+
@errors.push("Invalid URL")
|
56
|
+
return false
|
57
|
+
end
|
58
|
+
end
|
59
|
+
|
60
|
+
parse_contents
|
61
|
+
|
62
|
+
return @errors.size == 0
|
63
|
+
end
|
64
|
+
|
65
|
+
def parse_contents
|
66
|
+
begin
|
67
|
+
raw = @contents.split(/\n\n/)
|
68
|
+
@errors.push("Must have two line breaks between Attributes section and Links section") and return if raw.size < 2
|
69
|
+
|
70
|
+
@version = raw.first.split(/\n/).first
|
71
|
+
raw.first.split(/\n/)[1..-1].each do |attribute|
|
72
|
+
parts = attribute.split(":")
|
73
|
+
next if parts.size < 2
|
74
|
+
self.send(parts.first.downcase.gsub(/-/, "_") + "=", parts[1..-1].join(":").strip)
|
75
|
+
end
|
76
|
+
|
77
|
+
error_if :version, @version.nil? || @version.match(/ZSFF 1\.[0-9]/).nil?
|
78
|
+
error_if :author, @author.nil? || @author == ""
|
79
|
+
error_if :title, @title.nil? || @title == ""
|
80
|
+
error_if :site, @site.nil? || @site == ""
|
81
|
+
warn_if :site, @site.nil? || !is_valid_url?(@site)
|
82
|
+
warn_if :subtitle, @subtitle.nil? || @subtitle == ""
|
83
|
+
warn_if :copyright, @copyright.nil? || @copyright == ""
|
84
|
+
error_if :content_type, @content_type.nil? || @content_type.match(/.*\/.*/).nil?
|
85
|
+
|
86
|
+
items = raw.last.split(/\n/)
|
87
|
+
items.each do |item|
|
88
|
+
warnings.push("Item '#{item}' does not appear to be a valid URL") and next unless is_valid_url?(item)
|
89
|
+
unless item.match(/\.page$/)
|
90
|
+
content = items.select{|i|item.gsub(/\.(php|php3|asp|aspx|htm|cfm|html)$/, "") + ".page" == i}.first
|
91
|
+
@links.push({:link => item, :content => content})
|
92
|
+
end
|
93
|
+
end
|
94
|
+
#rescue
|
95
|
+
# @errors.push("Cannot parse ZSFF file")
|
96
|
+
end
|
97
|
+
|
98
|
+
end
|
99
|
+
|
100
|
+
private
|
101
|
+
def error_if(attribute, condition)
|
102
|
+
@errors.push("Invalid #{attribute.to_s.capitalize} declaration.") if condition
|
103
|
+
end
|
104
|
+
|
105
|
+
def warn_if(attribute, condition)
|
106
|
+
@warnings.push("#{attribute.to_s.capitalize} may be invalid.") if condition
|
107
|
+
end
|
108
|
+
|
109
|
+
def is_valid_url?(url)
|
110
|
+
!url.match(/(^$)|(^(http|https):\/\/[a-z0-9]+([\-\.]{1}[a-z0-9]+)*\.[a-z]{2,5}(([0-9]{1,5})?\/.*)?$)/ix).nil?
|
111
|
+
end
|
112
|
+
end
|
data/test/test_zsff.rb
ADDED
@@ -0,0 +1,113 @@
|
|
1
|
+
require 'test/unit'
|
2
|
+
require File.dirname(__FILE__) + '/../lib/zsff'
|
3
|
+
class ZsffTest < Test::Unit::TestCase
|
4
|
+
# Replace this with your real tests.
|
5
|
+
def test_parse_url
|
6
|
+
parser = Zsff.new(:url => "http://subwindow.com/articles.zsff")
|
7
|
+
|
8
|
+
assert_equal true, parser.parse
|
9
|
+
assert_equal [], parser.errors
|
10
|
+
assert_equal [], parser.warnings
|
11
|
+
assert_equal "ZSFF 1.0", parser.version
|
12
|
+
assert_equal "Erik Peterson", parser.author
|
13
|
+
assert_equal "subWindow Blog", parser.title
|
14
|
+
assert_equal "http://www.subwindow.com/", parser.site
|
15
|
+
assert_equal "Just another crappy programmer's blog", parser.subtitle
|
16
|
+
assert_equal "2008", parser.copyright
|
17
|
+
assert_equal "text/plain", parser.content_type
|
18
|
+
assert parser.links.size > 2
|
19
|
+
end
|
20
|
+
|
21
|
+
def test_static_parse_url
|
22
|
+
parser = Zsff::parse_url("http://subwindow.com/articles.zsff")
|
23
|
+
|
24
|
+
assert_equal [], parser.errors
|
25
|
+
assert_equal [], parser.warnings
|
26
|
+
end
|
27
|
+
|
28
|
+
def test_static_parse_contents
|
29
|
+
zsff = <<ZSFFSTR
|
30
|
+
ZSFF 1.0
|
31
|
+
Author: Erik Peterson
|
32
|
+
Title: subWindow Blog
|
33
|
+
Site: http://www.subwindow.com/
|
34
|
+
Subtitle: Just another crappy programmer's blog
|
35
|
+
Copyright: 2008
|
36
|
+
Content-type: text/plain
|
37
|
+
|
38
|
+
http://subwindow.com/articles/3.page
|
39
|
+
http://subwindow.com/articles/3.html
|
40
|
+
http://subwindow.com/articles/2
|
41
|
+
http://subwindow.com/articles/2.page
|
42
|
+
http://subwindow.com/articles/1
|
43
|
+
ZSFFSTR
|
44
|
+
|
45
|
+
parser = Zsff::parse_contents(zsff)
|
46
|
+
|
47
|
+
assert_equal [], parser.errors
|
48
|
+
assert_equal [], parser.warnings
|
49
|
+
end
|
50
|
+
|
51
|
+
def test_parse_string
|
52
|
+
zsff = <<ZSFFSTR
|
53
|
+
ZSFF 1.0
|
54
|
+
Author: Erik Peterson
|
55
|
+
Title: subWindow Blog
|
56
|
+
Site: http://www.subwindow.com/
|
57
|
+
Subtitle: Just another crappy programmer's blog
|
58
|
+
Copyright: 2008
|
59
|
+
Content-type: text/plain
|
60
|
+
|
61
|
+
http://subwindow.com/articles/3.page
|
62
|
+
http://subwindow.com/articles/3.html
|
63
|
+
http://subwindow.com/articles/2
|
64
|
+
http://subwindow.com/articles/2.page
|
65
|
+
http://subwindow.com/articles/1
|
66
|
+
ZSFFSTR
|
67
|
+
|
68
|
+
parser = Zsff.new(:contents => zsff)
|
69
|
+
assert_equal true, parser.parse
|
70
|
+
assert_equal [], parser.errors
|
71
|
+
assert_equal [], parser.warnings
|
72
|
+
assert_equal "ZSFF 1.0", parser.version
|
73
|
+
assert_equal "Erik Peterson", parser.author
|
74
|
+
assert_equal "subWindow Blog", parser.title
|
75
|
+
assert_equal "http://www.subwindow.com/", parser.site
|
76
|
+
assert_equal "Just another crappy programmer's blog", parser.subtitle
|
77
|
+
assert_equal "2008", parser.copyright
|
78
|
+
assert_equal "text/plain", parser.content_type
|
79
|
+
assert_equal 3, parser.links.size
|
80
|
+
assert_equal "http://subwindow.com/articles/3.html", parser.links[0][:link]
|
81
|
+
assert_equal "http://subwindow.com/articles/3.page", parser.links[0][:content]
|
82
|
+
assert_equal "http://subwindow.com/articles/2", parser.links[1][:link]
|
83
|
+
assert_equal "http://subwindow.com/articles/2.page", parser.links[1][:content]
|
84
|
+
assert_equal "http://subwindow.com/articles/1", parser.links[2][:link]
|
85
|
+
assert_equal nil, parser.links[2][:content]
|
86
|
+
end
|
87
|
+
|
88
|
+
def test_fail_parse
|
89
|
+
zsff = "THIS IS NOT A VALID ZSFF FEED"
|
90
|
+
|
91
|
+
parser = Zsff.new(:url => zsff)
|
92
|
+
assert_equal false, parser.parse
|
93
|
+
assert parser.errors.include?("Invalid URL")
|
94
|
+
end
|
95
|
+
|
96
|
+
def test_fail_links
|
97
|
+
zsff = <<ZSFFSTR
|
98
|
+
ZSFF 1.0
|
99
|
+
Author: Erik Peterson
|
100
|
+
Title: subWindow Blog
|
101
|
+
Site: http://www.subwindow.com/
|
102
|
+
Subtitle: Just another crappy programmer's blog
|
103
|
+
Copyright: 2008
|
104
|
+
Content-type: text/plain
|
105
|
+
http://subwindow.com/articles/3
|
106
|
+
http://subwindow.com/articles/2
|
107
|
+
ZSFFSTR
|
108
|
+
|
109
|
+
parser = Zsff.new(:contents => zsff)
|
110
|
+
assert_equal false, parser.parse
|
111
|
+
assert parser.errors.include?("Must have two line breaks between Attributes section and Links section")
|
112
|
+
end
|
113
|
+
end
|
metadata
ADDED
@@ -0,0 +1,69 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: zsff
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 1.0.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Erik Peterson
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
|
12
|
+
date: 2008-01-17 00:00:00 -05:00
|
13
|
+
default_executable:
|
14
|
+
dependencies:
|
15
|
+
- !ruby/object:Gem::Dependency
|
16
|
+
name: hoe
|
17
|
+
version_requirement:
|
18
|
+
version_requirements: !ruby/object:Gem::Requirement
|
19
|
+
requirements:
|
20
|
+
- - ">="
|
21
|
+
- !ruby/object:Gem::Version
|
22
|
+
version: 1.4.0
|
23
|
+
version:
|
24
|
+
description: "== FEATURES/PROBLEMS: Right now, only one function: parse. This does the validation and parsing all in one step. This is intended to be used by any reader (who would take care of what links have been read, etc). == SYNOPSIS: results = Zsff.parse(url) results[:errors] #Any errors encountered while parsing results[:warnings] #Any warnings encountered while parsing results[:attrs] #A hash for the author, title, etc information from the feed results[:links] #List of links in the feed == REQUIREMENTS:"
|
25
|
+
email: erik@subwindow.com
|
26
|
+
executables: []
|
27
|
+
|
28
|
+
extensions: []
|
29
|
+
|
30
|
+
extra_rdoc_files:
|
31
|
+
- History.txt
|
32
|
+
- Manifest.txt
|
33
|
+
- README.txt
|
34
|
+
files:
|
35
|
+
- History.txt
|
36
|
+
- Manifest.txt
|
37
|
+
- README.txt
|
38
|
+
- Rakefile
|
39
|
+
- lib/zsff.rb
|
40
|
+
- test/test_zsff.rb
|
41
|
+
has_rdoc: true
|
42
|
+
homepage: " by Erik Peterson"
|
43
|
+
post_install_message:
|
44
|
+
rdoc_options:
|
45
|
+
- --main
|
46
|
+
- README.txt
|
47
|
+
require_paths:
|
48
|
+
- lib
|
49
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
50
|
+
requirements:
|
51
|
+
- - ">="
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: "0"
|
54
|
+
version:
|
55
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
56
|
+
requirements:
|
57
|
+
- - ">="
|
58
|
+
- !ruby/object:Gem::Version
|
59
|
+
version: "0"
|
60
|
+
version:
|
61
|
+
requirements: []
|
62
|
+
|
63
|
+
rubyforge_project: zsff
|
64
|
+
rubygems_version: 1.0.1
|
65
|
+
signing_key:
|
66
|
+
specification_version: 2
|
67
|
+
summary: A parser/validator for ZSFF feeds
|
68
|
+
test_files:
|
69
|
+
- test/test_zsff.rb
|