httpspell 1.2.1 → 1.3.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/Gemfile.lock +57 -55
- data/TODO.markdown +6 -0
- data/lib/httpspell/spider.rb +14 -1
- data/lib/httpspell/version.rb +1 -1
- metadata +4 -4
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: ec39e7efff90e1b266f19714e6b6ce91a1a714e149be0df491e0e04cf5bef564
|
4
|
+
data.tar.gz: 58be9917fc0e13ad4653e6687b19b018d30be56b0c0c9d62da8e39ef169264e6
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 045cc45fc3bd73e5cb4694fec14dec5afad13ab8402cdc90173b621f21a8a11c0b02a375404e0dc332c7e6ec29a571ce3e6d5b152283ad6bb9323161f583579d
|
7
|
+
data.tar.gz: de4f50971f4d12a29c829b47a14f54d84c005c9ff7d421fcfcd672fdf065eb7db5ad4c27a83933e4d9de4bf4417d3cfbdf881a312416a0c6b0a95018637592f7
|
data/Gemfile.lock
CHANGED
@@ -1,51 +1,51 @@
|
|
1
1
|
PATH
|
2
2
|
remote: .
|
3
3
|
specs:
|
4
|
-
httpspell (1.
|
4
|
+
httpspell (1.3.0)
|
5
5
|
addressable
|
6
6
|
nokogiri
|
7
7
|
|
8
8
|
GEM
|
9
9
|
remote: https://rubygems.org/
|
10
10
|
specs:
|
11
|
-
addressable (2.
|
11
|
+
addressable (2.6.0)
|
12
12
|
public_suffix (>= 2.0.2, < 4.0)
|
13
|
-
aruba (0.14.
|
14
|
-
childprocess (>= 0.6.3, <
|
13
|
+
aruba (0.14.9)
|
14
|
+
childprocess (>= 0.6.3, < 1.1.0)
|
15
15
|
contracts (~> 0.9)
|
16
16
|
cucumber (>= 1.3.19)
|
17
|
-
ffi (~> 1.9
|
17
|
+
ffi (~> 1.9)
|
18
18
|
rspec-expectations (>= 2.99)
|
19
19
|
thor (~> 0.19)
|
20
20
|
ast (2.4.0)
|
21
|
-
backports (3.
|
21
|
+
backports (3.13.0)
|
22
22
|
builder (3.2.3)
|
23
|
-
byebug (
|
24
|
-
childprocess (0.
|
25
|
-
|
23
|
+
byebug (11.0.1)
|
24
|
+
childprocess (1.0.1)
|
25
|
+
rake (< 13.0)
|
26
26
|
coderay (1.1.2)
|
27
27
|
contracts (0.16.0)
|
28
|
-
cucumber (3.1.
|
28
|
+
cucumber (3.1.2)
|
29
29
|
builder (>= 2.1.2)
|
30
|
-
cucumber-core (~> 3.
|
31
|
-
cucumber-expressions (~>
|
30
|
+
cucumber-core (~> 3.2.0)
|
31
|
+
cucumber-expressions (~> 6.0.1)
|
32
32
|
cucumber-wire (~> 0.0.1)
|
33
33
|
diff-lcs (~> 1.3)
|
34
|
-
gherkin (~> 5.0)
|
34
|
+
gherkin (~> 5.1.0)
|
35
35
|
multi_json (>= 1.7.5, < 2.0)
|
36
36
|
multi_test (>= 0.1.2)
|
37
|
-
cucumber-core (3.1
|
37
|
+
cucumber-core (3.2.1)
|
38
38
|
backports (>= 3.8.0)
|
39
39
|
cucumber-tag_expressions (~> 1.1.0)
|
40
|
-
gherkin (
|
41
|
-
cucumber-expressions (
|
40
|
+
gherkin (~> 5.0)
|
41
|
+
cucumber-expressions (6.0.1)
|
42
42
|
cucumber-tag_expressions (1.1.1)
|
43
43
|
cucumber-wire (0.0.1)
|
44
44
|
diff-lcs (1.3)
|
45
|
-
ffi (1.
|
45
|
+
ffi (1.10.0)
|
46
46
|
formatador (0.2.5)
|
47
47
|
gherkin (5.1.0)
|
48
|
-
guard (2.
|
48
|
+
guard (2.15.0)
|
49
49
|
formatador (>= 0.2.4)
|
50
50
|
listen (>= 2.7, < 4.0)
|
51
51
|
lumberjack (>= 1.0.12, < 2.0)
|
@@ -54,8 +54,8 @@ GEM
|
|
54
54
|
pry (>= 0.9.12)
|
55
55
|
shellany (~> 0.0)
|
56
56
|
thor (>= 0.18.1)
|
57
|
-
guard-bundler (2.1
|
58
|
-
bundler (
|
57
|
+
guard-bundler (2.2.1)
|
58
|
+
bundler (>= 1.3.0, < 3)
|
59
59
|
guard (~> 2.2)
|
60
60
|
guard-compat (~> 1.1)
|
61
61
|
guard-compat (1.2.1)
|
@@ -63,65 +63,67 @@ GEM
|
|
63
63
|
guard (~> 2.1)
|
64
64
|
guard-compat (~> 1.1)
|
65
65
|
rspec (>= 2.99.0, < 4.0)
|
66
|
+
jaro_winkler (1.5.2)
|
66
67
|
listen (3.1.5)
|
67
68
|
rb-fsevent (~> 0.9, >= 0.9.4)
|
68
69
|
rb-inotify (~> 0.9, >= 0.9.7)
|
69
70
|
ruby_dep (~> 1.2)
|
70
71
|
lumberjack (1.0.13)
|
71
|
-
method_source (0.9.
|
72
|
-
mini_portile2 (2.
|
72
|
+
method_source (0.9.2)
|
73
|
+
mini_portile2 (2.4.0)
|
73
74
|
multi_json (1.13.1)
|
74
75
|
multi_test (0.1.2)
|
75
76
|
nenv (0.3.0)
|
76
|
-
nokogiri (1.
|
77
|
-
mini_portile2 (~> 2.
|
77
|
+
nokogiri (1.10.2)
|
78
|
+
mini_portile2 (~> 2.4.0)
|
78
79
|
notiffany (0.1.1)
|
79
80
|
nenv (~> 0.1)
|
80
81
|
shellany (~> 0.0)
|
81
|
-
parallel (1.
|
82
|
-
parser (2.
|
82
|
+
parallel (1.17.0)
|
83
|
+
parser (2.6.2.1)
|
83
84
|
ast (~> 2.4.0)
|
84
|
-
|
85
|
-
pry (0.11.3)
|
85
|
+
pry (0.12.2)
|
86
86
|
coderay (~> 1.1.0)
|
87
87
|
method_source (~> 0.9.0)
|
88
|
-
pry-byebug (3.
|
89
|
-
byebug (~>
|
88
|
+
pry-byebug (3.7.0)
|
89
|
+
byebug (~> 11.0)
|
90
90
|
pry (~> 0.10)
|
91
|
-
|
92
|
-
|
91
|
+
psych (3.1.0)
|
92
|
+
public_suffix (3.0.3)
|
93
|
+
rack (2.0.7)
|
93
94
|
rainbow (3.0.0)
|
94
|
-
rake (12.3.
|
95
|
+
rake (12.3.2)
|
95
96
|
rb-fsevent (0.10.3)
|
96
|
-
rb-inotify (0.
|
97
|
-
ffi (
|
98
|
-
rspec (3.
|
99
|
-
rspec-core (~> 3.
|
100
|
-
rspec-expectations (~> 3.
|
101
|
-
rspec-mocks (~> 3.
|
102
|
-
rspec-core (3.
|
103
|
-
rspec-support (~> 3.
|
104
|
-
rspec-expectations (3.
|
97
|
+
rb-inotify (0.10.0)
|
98
|
+
ffi (~> 1.0)
|
99
|
+
rspec (3.8.0)
|
100
|
+
rspec-core (~> 3.8.0)
|
101
|
+
rspec-expectations (~> 3.8.0)
|
102
|
+
rspec-mocks (~> 3.8.0)
|
103
|
+
rspec-core (3.8.0)
|
104
|
+
rspec-support (~> 3.8.0)
|
105
|
+
rspec-expectations (3.8.2)
|
105
106
|
diff-lcs (>= 1.2.0, < 2.0)
|
106
|
-
rspec-support (~> 3.
|
107
|
-
rspec-mocks (3.
|
107
|
+
rspec-support (~> 3.8.0)
|
108
|
+
rspec-mocks (3.8.0)
|
108
109
|
diff-lcs (>= 1.2.0, < 2.0)
|
109
|
-
rspec-support (~> 3.
|
110
|
-
rspec-support (3.
|
111
|
-
rubocop (0.
|
110
|
+
rspec-support (~> 3.8.0)
|
111
|
+
rspec-support (3.8.0)
|
112
|
+
rubocop (0.67.2)
|
113
|
+
jaro_winkler (~> 1.5.1)
|
112
114
|
parallel (~> 1.10)
|
113
|
-
parser (>= 2.5)
|
114
|
-
|
115
|
+
parser (>= 2.5, != 2.5.1.1)
|
116
|
+
psych (>= 3.1.0)
|
115
117
|
rainbow (>= 2.2.2, < 4.0)
|
116
118
|
ruby-progressbar (~> 1.7)
|
117
|
-
unicode-display_width (
|
118
|
-
ruby-progressbar (1.
|
119
|
+
unicode-display_width (>= 1.4.0, < 1.6)
|
120
|
+
ruby-progressbar (1.10.0)
|
119
121
|
ruby_dep (1.5.0)
|
120
122
|
shellany (0.0.1)
|
121
|
-
stub_server (0.
|
123
|
+
stub_server (0.4.0)
|
122
124
|
rack
|
123
|
-
thor (0.20.
|
124
|
-
unicode-display_width (1.
|
125
|
+
thor (0.20.3)
|
126
|
+
unicode-display_width (1.5.0)
|
125
127
|
|
126
128
|
PLATFORMS
|
127
129
|
ruby
|
@@ -141,4 +143,4 @@ DEPENDENCIES
|
|
141
143
|
stub_server
|
142
144
|
|
143
145
|
BUNDLED WITH
|
144
|
-
1.
|
146
|
+
1.17.2
|
data/TODO.markdown
ADDED
@@ -0,0 +1,6 @@
|
|
1
|
+
* Bail out if lang cannot be inferred and is not given on cmdline
|
2
|
+
* exe/httpspell: # TODO: --recursive, defaults to false
|
3
|
+
* exe/httpspell: # TODO wget has some additional options for recursive behavior that should be reviewed
|
4
|
+
* exe/httpspell: # TODO: Find sections with a lang attribute and handle them separately
|
5
|
+
* lib/httpspell/spider.rb: # TODO Print _which_ entry of the blacklist matches
|
6
|
+
* lib/httpspell/spider.rb: # TODO Ignore same page links (some anchor)
|
data/lib/httpspell/spider.rb
CHANGED
@@ -46,7 +46,7 @@ module HttpSpell
|
|
46
46
|
private
|
47
47
|
|
48
48
|
def links(uri)
|
49
|
-
response = URI(uri)
|
49
|
+
response = http_get(URI(uri))
|
50
50
|
|
51
51
|
if response.content_type != 'text/html'
|
52
52
|
warn "Skipping #{uri} because it is not HTML" if @tracing
|
@@ -82,5 +82,18 @@ module HttpSpell
|
|
82
82
|
warn "Adding #{links.size} links from #{uri}" if @tracing
|
83
83
|
links
|
84
84
|
end
|
85
|
+
|
86
|
+
# https://twin.github.io/improving-open-uri/
|
87
|
+
def http_get(uri)
|
88
|
+
tries = 10
|
89
|
+
|
90
|
+
begin
|
91
|
+
uri.open(redirect: false)
|
92
|
+
rescue OpenURI::HTTPRedirect => redirect
|
93
|
+
uri = redirect.uri
|
94
|
+
retry if (tries -= 1) > 0
|
95
|
+
raise
|
96
|
+
end
|
97
|
+
end
|
85
98
|
end
|
86
99
|
end
|
data/lib/httpspell/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: httpspell
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.
|
4
|
+
version: 1.3.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Steffen Uhlig
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2019-04-12 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: addressable
|
@@ -211,6 +211,7 @@ files:
|
|
211
211
|
- Gemfile.lock
|
212
212
|
- README.markdown
|
213
213
|
- Rakefile
|
214
|
+
- TODO.markdown
|
214
215
|
- exe/httpspell
|
215
216
|
- httpspell.gemspec
|
216
217
|
- lib/httpspell/spellchecker.rb
|
@@ -235,8 +236,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
235
236
|
- !ruby/object:Gem::Version
|
236
237
|
version: '0'
|
237
238
|
requirements: []
|
238
|
-
|
239
|
-
rubygems_version: 2.7.6
|
239
|
+
rubygems_version: 3.0.1
|
240
240
|
signing_key:
|
241
241
|
specification_version: 4
|
242
242
|
summary: HTTP spellchecker
|