postrank-uri 1.0.17 → 1.0.18
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/README.md +3 -3
- data/lib/postrank-uri.rb +12 -11
- data/lib/postrank-uri/{c18n.yml → c14n.yml} +2 -0
- data/lib/postrank-uri/version.rb +1 -1
- data/postrank-uri.gemspec +2 -2
- data/spec/{c18n_hosts.yml → c14n_hosts.yml} +0 -0
- data/spec/postrank-uri_spec.rb +24 -6
- metadata +16 -26
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 1f9a235d0c2287732278b672997027c7d4093d0f
|
4
|
+
data.tar.gz: 8c91e4b1c787c43e6ea2ccc51593be3809746fa7
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: c702922f05473c762d7223777eb48641db8c4b0e156539c729433f3aa9174b010bce707801ee8c7ec310e4181edb3402c77131d3a66b0bdc02e99f87c1d9982a
|
7
|
+
data.tar.gz: 06040dead1c6348febb64211e2787216c287c87baa09555947e03a4bea09b7293ed33faed08851e28aaa2ff08389d121a48746cc6a6f3af6c7e023f75db1917a
|
data/README.md
CHANGED
@@ -14,7 +14,7 @@ In a nutshell, we need to make sure that creative cases like the ones below all
|
|
14
14
|
## API
|
15
15
|
|
16
16
|
- **PostRank::URI.extract(text)** - Detect URIs in text, discard bad TLD's
|
17
|
-
- **PostRank::URI.clean(uri)** - Unescape, normalize, apply
|
17
|
+
- **PostRank::URI.clean(uri)** - Unescape, normalize, apply c14n filters - 95% use case.
|
18
18
|
|
19
19
|
- **PostRank::URI.normalize(uri)** - Apply RFC normalization rules, discard extra path characters, drop anchors
|
20
20
|
- **PostRank::URI.unescape(uri)** - Unescape URI entities, handle +/%20's, etc
|
@@ -33,8 +33,8 @@ In a nutshell, we need to make sure that creative cases like the ones below all
|
|
33
33
|
[0] "http://link.to/?a=b"
|
34
34
|
]
|
35
35
|
|
36
|
-
##
|
36
|
+
## C14N
|
37
37
|
|
38
|
-
As part of URI canonicalization the library will remove common tracking parameters from Google Analytics and several other providers. Beyond that, host-specific rules are also applied. For example, nytimes.com likes to add a 'partner' query parameter for tracking purposes, but which has no effect on the content - hence, it is removed from the URI. For full list, see the
|
38
|
+
As part of URI canonicalization the library will remove common tracking parameters from Google Analytics and several other providers. Beyond that, host-specific rules are also applied. For example, nytimes.com likes to add a 'partner' query parameter for tracking purposes, but which has no effect on the content - hence, it is removed from the URI. For full list, see the c14n.yml file.
|
39
39
|
|
40
40
|
Detecting "duplicate URLs" is a hard problem to solve (expensive in all senses), instead we are compiling a manually assembled database. If you find cases which are missing, please do report them, or send us a pull request!
|
data/lib/postrank-uri.rb
CHANGED
@@ -1,4 +1,3 @@
|
|
1
|
-
# -*- encoding: utf-8 -*-
|
2
1
|
|
3
2
|
require 'addressable/uri'
|
4
3
|
require 'digest/md5'
|
@@ -34,11 +33,11 @@ end
|
|
34
33
|
module PostRank
|
35
34
|
module URI
|
36
35
|
|
37
|
-
|
36
|
+
c14ndb = YAML.load_file(File.dirname(__FILE__) + '/postrank-uri/c14n.yml')
|
38
37
|
|
39
|
-
|
40
|
-
|
41
|
-
|
38
|
+
C14N = {}
|
39
|
+
C14N[:global] = c14ndb[:all].freeze
|
40
|
+
C14N[:hosts] = c14ndb[:hosts].inject({}) {|h,(k,v)| h[/#{Regexp.escape(k)}$/.freeze] = v; h}
|
42
41
|
|
43
42
|
URIREGEX = {}
|
44
43
|
URIREGEX[:protocol] = /https?:\/\//i
|
@@ -130,13 +129,15 @@ module PostRank
|
|
130
129
|
end
|
131
130
|
|
132
131
|
def unescape(uri)
|
133
|
-
|
132
|
+
u = parse(uri)
|
133
|
+
u.query = u.query.tr('+', ' ') if u.query
|
134
|
+
u.to_s.gsub(URIREGEX[:unescape]) do
|
134
135
|
[$1.delete('%')].pack('H*')
|
135
136
|
end
|
136
137
|
end
|
137
138
|
|
138
139
|
def clean(uri, opts = {})
|
139
|
-
uri = normalize(
|
140
|
+
uri = normalize(c14n(unescape(uri), opts))
|
140
141
|
opts[:raw] ? uri : uri.to_s
|
141
142
|
end
|
142
143
|
|
@@ -153,13 +154,13 @@ module PostRank
|
|
153
154
|
u
|
154
155
|
end
|
155
156
|
|
156
|
-
def
|
157
|
+
def c14n(uri, opts = {})
|
157
158
|
u = parse(uri, opts)
|
158
159
|
u = embedded(u)
|
159
160
|
|
160
161
|
if q = u.query_values(Array)
|
161
|
-
q.delete_if { |k,v|
|
162
|
-
q.delete_if { |k,v|
|
162
|
+
q.delete_if { |k,v| C14N[:global].include?(k) }
|
163
|
+
q.delete_if { |k,v| C14N[:hosts].find {|r,p| u.host =~ r && p.include?(k) } }
|
163
164
|
end
|
164
165
|
u.query_values = q
|
165
166
|
|
@@ -224,7 +225,7 @@ module PostRank
|
|
224
225
|
cleaned_uri = clean(uri, :raw => true)
|
225
226
|
|
226
227
|
if host = cleaned_uri.host
|
227
|
-
is_valid = PublicSuffix.valid?(host)
|
228
|
+
is_valid = PublicSuffix.valid?(Addressable::IDNA.to_unicode(host))
|
228
229
|
end
|
229
230
|
|
230
231
|
is_valid
|
data/lib/postrank-uri/version.rb
CHANGED
data/postrank-uri.gemspec
CHANGED
@@ -9,14 +9,14 @@ Gem::Specification.new do |s|
|
|
9
9
|
s.authors = ["Ilya Grigorik"]
|
10
10
|
s.email = ["ilya@igvita.com"]
|
11
11
|
s.homepage = "http://github.com/postrank-labs/postrank-uri"
|
12
|
-
s.summary = "URI normalization,
|
12
|
+
s.summary = "URI normalization, c14n, escaping, and extraction"
|
13
13
|
s.description = s.summary
|
14
14
|
|
15
15
|
s.rubyforge_project = "postrank-uri"
|
16
16
|
|
17
17
|
s.add_dependency "addressable", "~> 2.3.0"
|
18
18
|
s.add_dependency "public_suffix", "~> 1.1.3"
|
19
|
-
s.add_dependency "nokogiri", "~> 1.
|
19
|
+
s.add_dependency "nokogiri", "~> 1.6.1"
|
20
20
|
|
21
21
|
s.add_development_dependency "rspec"
|
22
22
|
|
File without changes
|
data/spec/postrank-uri_spec.rb
CHANGED
@@ -29,15 +29,19 @@ describe PostRank::URI do
|
|
29
29
|
# See http://tools.ietf.org/html/rfc3986#section-2.3
|
30
30
|
|
31
31
|
it "should unescape PostRank::URI with spaces encoded as '+'" do
|
32
|
-
PostRank::URI.unescape('id=+1').should == 'id= 1'
|
32
|
+
PostRank::URI.unescape('?id=+1').should == '?id= 1'
|
33
33
|
end
|
34
34
|
|
35
35
|
it "should unescape PostRank::URI with spaces encoded as '+'" do
|
36
|
-
PostRank::URI.unescape('id%3D+1').should == 'id= 1'
|
36
|
+
PostRank::URI.unescape('?id%3D+1').should == '?id= 1'
|
37
37
|
end
|
38
38
|
|
39
39
|
it "should unescape PostRank::URI with spaces encoded as %20" do
|
40
|
-
PostRank::URI.unescape('id=%201').should == 'id= 1'
|
40
|
+
PostRank::URI.unescape('?id=%201').should == '?id= 1'
|
41
|
+
end
|
42
|
+
|
43
|
+
it "should not unescape '+' to spaces in paths" do
|
44
|
+
PostRank::URI.unescape('/foo+bar?id=foo+bar').should == '/foo+bar?id=foo bar'
|
41
45
|
end
|
42
46
|
end
|
43
47
|
|
@@ -100,7 +104,7 @@ describe PostRank::URI do
|
|
100
104
|
|
101
105
|
context "canonicalization" do
|
102
106
|
def c(uri)
|
103
|
-
PostRank::URI.
|
107
|
+
PostRank::URI.c14n(uri).to_s
|
104
108
|
end
|
105
109
|
|
106
110
|
context "query parameters" do
|
@@ -122,6 +126,12 @@ describe PostRank::URI do
|
|
122
126
|
c('igvita.com/?id=a&utm_source=a&awesm=b').should == 'http://igvita.com/?id=a'
|
123
127
|
c('igvita.com/?id=a&sms_ss=a').should == 'http://igvita.com/?id=a'
|
124
128
|
end
|
129
|
+
|
130
|
+
it "should remove PHPSESSID parameter" do
|
131
|
+
c('http://www.nachi.org/forum?PHPSESSID=9ee2fb10b7274ef2b15d1d4006b8c8dd').should == 'http://www.nachi.org/forum?'
|
132
|
+
c('http://www.nachi.org/forum/?PHPSESSID=9ee2fb10b7274ef2b15d1d4006b8c8dd').should == 'http://www.nachi.org/forum/?'
|
133
|
+
c('http://www.nachi.org/forum?id=123&PHPSESSID=9ee2fb10b7274ef2b15d1d4006b8c8dd').should == 'http://www.nachi.org/forum?id=123'
|
134
|
+
end
|
125
135
|
end
|
126
136
|
|
127
137
|
context "hashbang" do
|
@@ -162,7 +172,7 @@ describe PostRank::URI do
|
|
162
172
|
PostRank::URI.clean(uri)
|
163
173
|
end
|
164
174
|
|
165
|
-
it "should unescape,
|
175
|
+
it "should unescape, c14n and normalize" do
|
166
176
|
c('http://igvita.com/?id=1').should == 'http://igvita.com/?id=1'
|
167
177
|
c('igvita.com/?id=1').should == 'http://igvita.com/?id=1'
|
168
178
|
|
@@ -179,7 +189,7 @@ describe PostRank::URI do
|
|
179
189
|
end
|
180
190
|
|
181
191
|
it "should clean host specific parameters" do
|
182
|
-
YAML.load_file('spec/
|
192
|
+
YAML.load_file('spec/c14n_hosts.yml').each do |orig, clean|
|
183
193
|
c(orig).should == clean
|
184
194
|
end
|
185
195
|
end
|
@@ -350,5 +360,13 @@ describe PostRank::URI do
|
|
350
360
|
it 'marks www.test.com as valid' do
|
351
361
|
PostRank::URI.valid?('http://www.test.com').should be_true
|
352
362
|
end
|
363
|
+
|
364
|
+
it 'marks Unicode domain as valid (NOTE: works only with a scheme)' do
|
365
|
+
PostRank::URI.valid?('http://президент.рф').should be_true
|
366
|
+
end
|
367
|
+
|
368
|
+
it 'marks punycode domain domain as valid' do
|
369
|
+
PostRank::URI.valid?('xn--d1abbgf6aiiy.xn--p1ai').should be_true
|
370
|
+
end
|
353
371
|
end
|
354
372
|
end
|
metadata
CHANGED
@@ -1,20 +1,18 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: postrank-uri
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.0.
|
5
|
-
prerelease:
|
4
|
+
version: 1.0.18
|
6
5
|
platform: ruby
|
7
6
|
authors:
|
8
7
|
- Ilya Grigorik
|
9
8
|
autorequire:
|
10
9
|
bindir: bin
|
11
10
|
cert_chain: []
|
12
|
-
date:
|
11
|
+
date: 2014-04-10 00:00:00.000000000 Z
|
13
12
|
dependencies:
|
14
13
|
- !ruby/object:Gem::Dependency
|
15
14
|
name: addressable
|
16
15
|
requirement: !ruby/object:Gem::Requirement
|
17
|
-
none: false
|
18
16
|
requirements:
|
19
17
|
- - ~>
|
20
18
|
- !ruby/object:Gem::Version
|
@@ -22,7 +20,6 @@ dependencies:
|
|
22
20
|
type: :runtime
|
23
21
|
prerelease: false
|
24
22
|
version_requirements: !ruby/object:Gem::Requirement
|
25
|
-
none: false
|
26
23
|
requirements:
|
27
24
|
- - ~>
|
28
25
|
- !ruby/object:Gem::Version
|
@@ -30,7 +27,6 @@ dependencies:
|
|
30
27
|
- !ruby/object:Gem::Dependency
|
31
28
|
name: public_suffix
|
32
29
|
requirement: !ruby/object:Gem::Requirement
|
33
|
-
none: false
|
34
30
|
requirements:
|
35
31
|
- - ~>
|
36
32
|
- !ruby/object:Gem::Version
|
@@ -38,7 +34,6 @@ dependencies:
|
|
38
34
|
type: :runtime
|
39
35
|
prerelease: false
|
40
36
|
version_requirements: !ruby/object:Gem::Requirement
|
41
|
-
none: false
|
42
37
|
requirements:
|
43
38
|
- - ~>
|
44
39
|
- !ruby/object:Gem::Version
|
@@ -46,36 +41,32 @@ dependencies:
|
|
46
41
|
- !ruby/object:Gem::Dependency
|
47
42
|
name: nokogiri
|
48
43
|
requirement: !ruby/object:Gem::Requirement
|
49
|
-
none: false
|
50
44
|
requirements:
|
51
45
|
- - ~>
|
52
46
|
- !ruby/object:Gem::Version
|
53
|
-
version: 1.
|
47
|
+
version: 1.6.1
|
54
48
|
type: :runtime
|
55
49
|
prerelease: false
|
56
50
|
version_requirements: !ruby/object:Gem::Requirement
|
57
|
-
none: false
|
58
51
|
requirements:
|
59
52
|
- - ~>
|
60
53
|
- !ruby/object:Gem::Version
|
61
|
-
version: 1.
|
54
|
+
version: 1.6.1
|
62
55
|
- !ruby/object:Gem::Dependency
|
63
56
|
name: rspec
|
64
57
|
requirement: !ruby/object:Gem::Requirement
|
65
|
-
none: false
|
66
58
|
requirements:
|
67
|
-
- -
|
59
|
+
- - '>='
|
68
60
|
- !ruby/object:Gem::Version
|
69
61
|
version: '0'
|
70
62
|
type: :development
|
71
63
|
prerelease: false
|
72
64
|
version_requirements: !ruby/object:Gem::Requirement
|
73
|
-
none: false
|
74
65
|
requirements:
|
75
|
-
- -
|
66
|
+
- - '>='
|
76
67
|
- !ruby/object:Gem::Version
|
77
68
|
version: '0'
|
78
|
-
description: URI normalization,
|
69
|
+
description: URI normalization, c14n, escaping, and extraction
|
79
70
|
email:
|
80
71
|
- ilya@igvita.com
|
81
72
|
executables: []
|
@@ -88,38 +79,37 @@ files:
|
|
88
79
|
- README.md
|
89
80
|
- Rakefile
|
90
81
|
- lib/postrank-uri.rb
|
91
|
-
- lib/postrank-uri/
|
82
|
+
- lib/postrank-uri/c14n.yml
|
92
83
|
- lib/postrank-uri/version.rb
|
93
84
|
- postrank-uri.gemspec
|
94
|
-
- spec/
|
85
|
+
- spec/c14n_hosts.yml
|
95
86
|
- spec/helper.rb
|
96
87
|
- spec/postrank-uri_spec.rb
|
97
88
|
homepage: http://github.com/postrank-labs/postrank-uri
|
98
89
|
licenses: []
|
90
|
+
metadata: {}
|
99
91
|
post_install_message:
|
100
92
|
rdoc_options: []
|
101
93
|
require_paths:
|
102
94
|
- lib
|
103
95
|
required_ruby_version: !ruby/object:Gem::Requirement
|
104
|
-
none: false
|
105
96
|
requirements:
|
106
|
-
- -
|
97
|
+
- - '>='
|
107
98
|
- !ruby/object:Gem::Version
|
108
99
|
version: '0'
|
109
100
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
110
|
-
none: false
|
111
101
|
requirements:
|
112
|
-
- -
|
102
|
+
- - '>='
|
113
103
|
- !ruby/object:Gem::Version
|
114
104
|
version: '0'
|
115
105
|
requirements: []
|
116
106
|
rubyforge_project: postrank-uri
|
117
|
-
rubygems_version:
|
107
|
+
rubygems_version: 2.0.6
|
118
108
|
signing_key:
|
119
|
-
specification_version:
|
120
|
-
summary: URI normalization,
|
109
|
+
specification_version: 4
|
110
|
+
summary: URI normalization, c14n, escaping, and extraction
|
121
111
|
test_files:
|
122
|
-
- spec/
|
112
|
+
- spec/c14n_hosts.yml
|
123
113
|
- spec/helper.rb
|
124
114
|
- spec/postrank-uri_spec.rb
|
125
115
|
has_rdoc:
|