wikirofs 0.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/.gitignore +9 -0
- data/Gemfile +4 -0
- data/LICENSE +116 -0
- data/README.md +79 -0
- data/Rakefile +2 -0
- data/bin/console +14 -0
- data/bin/mount.wikiro +1 -0
- data/bin/setup +8 -0
- data/lib/wikipedia.rb +123 -0
- data/lib/wikirofs/version.rb +3 -0
- data/lib/wikirofs.rb +5 -0
- data/main.rb +176 -0
- data/wikirofs.gemspec +30 -0
- metadata +128 -0
checksums.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
---
|
|
2
|
+
SHA1:
|
|
3
|
+
metadata.gz: cba44ca62b8cb045b951ccd57c9e899ac8a5f95c
|
|
4
|
+
data.tar.gz: 15eedefef3efbd3d8a5c7047a522bd7912270bfd
|
|
5
|
+
SHA512:
|
|
6
|
+
metadata.gz: 9ddb38ae2d2f4edf988abb0e746440a071ea67928d058360019833e698e50eba9bb9a6d91a72972fb90a741bd1030f25ae9c999fe9f48def7287b42f00c938f9
|
|
7
|
+
data.tar.gz: 2dbd8461445fa3e851fca87a4eb85c84626fa3cd32304c2b4aea8d03fcb98c25310ee42bc9731db470408193db5c8a173f01c0cce76366cdbaa7d3b51b57c5c3
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE
ADDED
|
@@ -0,0 +1,116 @@
|
|
|
1
|
+
CC0 1.0 Universal
|
|
2
|
+
|
|
3
|
+
Statement of Purpose
|
|
4
|
+
|
|
5
|
+
The laws of most jurisdictions throughout the world automatically confer
|
|
6
|
+
exclusive Copyright and Related Rights (defined below) upon the creator and
|
|
7
|
+
subsequent owner(s) (each and all, an "owner") of an original work of
|
|
8
|
+
authorship and/or a database (each, a "Work").
|
|
9
|
+
|
|
10
|
+
Certain owners wish to permanently relinquish those rights to a Work for the
|
|
11
|
+
purpose of contributing to a commons of creative, cultural and scientific
|
|
12
|
+
works ("Commons") that the public can reliably and without fear of later
|
|
13
|
+
claims of infringement build upon, modify, incorporate in other works, reuse
|
|
14
|
+
and redistribute as freely as possible in any form whatsoever and for any
|
|
15
|
+
purposes, including without limitation commercial purposes. These owners may
|
|
16
|
+
contribute to the Commons to promote the ideal of a free culture and the
|
|
17
|
+
further production of creative, cultural and scientific works, or to gain
|
|
18
|
+
reputation or greater distribution for their Work in part through the use and
|
|
19
|
+
efforts of others.
|
|
20
|
+
|
|
21
|
+
For these and/or other purposes and motivations, and without any expectation
|
|
22
|
+
of additional consideration or compensation, the person associating CC0 with a
|
|
23
|
+
Work (the "Affirmer"), to the extent that he or she is an owner of Copyright
|
|
24
|
+
and Related Rights in the Work, voluntarily elects to apply CC0 to the Work
|
|
25
|
+
and publicly distribute the Work under its terms, with knowledge of his or her
|
|
26
|
+
Copyright and Related Rights in the Work and the meaning and intended legal
|
|
27
|
+
effect of CC0 on those rights.
|
|
28
|
+
|
|
29
|
+
1. Copyright and Related Rights. A Work made available under CC0 may be
|
|
30
|
+
protected by copyright and related or neighboring rights ("Copyright and
|
|
31
|
+
Related Rights"). Copyright and Related Rights include, but are not limited
|
|
32
|
+
to, the following:
|
|
33
|
+
|
|
34
|
+
i. the right to reproduce, adapt, distribute, perform, display, communicate,
|
|
35
|
+
and translate a Work;
|
|
36
|
+
|
|
37
|
+
ii. moral rights retained by the original author(s) and/or performer(s);
|
|
38
|
+
|
|
39
|
+
iii. publicity and privacy rights pertaining to a person's image or likeness
|
|
40
|
+
depicted in a Work;
|
|
41
|
+
|
|
42
|
+
iv. rights protecting against unfair competition in regards to a Work,
|
|
43
|
+
subject to the limitations in paragraph 4(a), below;
|
|
44
|
+
|
|
45
|
+
v. rights protecting the extraction, dissemination, use and reuse of data in
|
|
46
|
+
a Work;
|
|
47
|
+
|
|
48
|
+
vi. database rights (such as those arising under Directive 96/9/EC of the
|
|
49
|
+
European Parliament and of the Council of 11 March 1996 on the legal
|
|
50
|
+
protection of databases, and under any national implementation thereof,
|
|
51
|
+
including any amended or successor version of such directive); and
|
|
52
|
+
|
|
53
|
+
vii. other similar, equivalent or corresponding rights throughout the world
|
|
54
|
+
based on applicable law or treaty, and any national implementations thereof.
|
|
55
|
+
|
|
56
|
+
2. Waiver. To the greatest extent permitted by, but not in contravention of,
|
|
57
|
+
applicable law, Affirmer hereby overtly, fully, permanently, irrevocably and
|
|
58
|
+
unconditionally waives, abandons, and surrenders all of Affirmer's Copyright
|
|
59
|
+
and Related Rights and associated claims and causes of action, whether now
|
|
60
|
+
known or unknown (including existing as well as future claims and causes of
|
|
61
|
+
action), in the Work (i) in all territories worldwide, (ii) for the maximum
|
|
62
|
+
duration provided by applicable law or treaty (including future time
|
|
63
|
+
extensions), (iii) in any current or future medium and for any number of
|
|
64
|
+
copies, and (iv) for any purpose whatsoever, including without limitation
|
|
65
|
+
commercial, advertising or promotional purposes (the "Waiver"). Affirmer makes
|
|
66
|
+
the Waiver for the benefit of each member of the public at large and to the
|
|
67
|
+
detriment of Affirmer's heirs and successors, fully intending that such Waiver
|
|
68
|
+
shall not be subject to revocation, rescission, cancellation, termination, or
|
|
69
|
+
any other legal or equitable action to disrupt the quiet enjoyment of the Work
|
|
70
|
+
by the public as contemplated by Affirmer's express Statement of Purpose.
|
|
71
|
+
|
|
72
|
+
3. Public License Fallback. Should any part of the Waiver for any reason be
|
|
73
|
+
judged legally invalid or ineffective under applicable law, then the Waiver
|
|
74
|
+
shall be preserved to the maximum extent permitted taking into account
|
|
75
|
+
Affirmer's express Statement of Purpose. In addition, to the extent the Waiver
|
|
76
|
+
is so judged Affirmer hereby grants to each affected person a royalty-free,
|
|
77
|
+
non transferable, non sublicensable, non exclusive, irrevocable and
|
|
78
|
+
unconditional license to exercise Affirmer's Copyright and Related Rights in
|
|
79
|
+
the Work (i) in all territories worldwide, (ii) for the maximum duration
|
|
80
|
+
provided by applicable law or treaty (including future time extensions), (iii)
|
|
81
|
+
in any current or future medium and for any number of copies, and (iv) for any
|
|
82
|
+
purpose whatsoever, including without limitation commercial, advertising or
|
|
83
|
+
promotional purposes (the "License"). The License shall be deemed effective as
|
|
84
|
+
of the date CC0 was applied by Affirmer to the Work. Should any part of the
|
|
85
|
+
License for any reason be judged legally invalid or ineffective under
|
|
86
|
+
applicable law, such partial invalidity or ineffectiveness shall not
|
|
87
|
+
invalidate the remainder of the License, and in such case Affirmer hereby
|
|
88
|
+
affirms that he or she will not (i) exercise any of his or her remaining
|
|
89
|
+
Copyright and Related Rights in the Work or (ii) assert any associated claims
|
|
90
|
+
and causes of action with respect to the Work, in either case contrary to
|
|
91
|
+
Affirmer's express Statement of Purpose.
|
|
92
|
+
|
|
93
|
+
4. Limitations and Disclaimers.
|
|
94
|
+
|
|
95
|
+
a. No trademark or patent rights held by Affirmer are waived, abandoned,
|
|
96
|
+
surrendered, licensed or otherwise affected by this document.
|
|
97
|
+
|
|
98
|
+
b. Affirmer offers the Work as-is and makes no representations or warranties
|
|
99
|
+
of any kind concerning the Work, express, implied, statutory or otherwise,
|
|
100
|
+
including without limitation warranties of title, merchantability, fitness
|
|
101
|
+
for a particular purpose, non infringement, or the absence of latent or
|
|
102
|
+
other defects, accuracy, or the present or absence of errors, whether or not
|
|
103
|
+
discoverable, all to the greatest extent permissible under applicable law.
|
|
104
|
+
|
|
105
|
+
c. Affirmer disclaims responsibility for clearing rights of other persons
|
|
106
|
+
that may apply to the Work or any use thereof, including without limitation
|
|
107
|
+
any person's Copyright and Related Rights in the Work. Further, Affirmer
|
|
108
|
+
disclaims responsibility for obtaining any necessary consents, permissions
|
|
109
|
+
or other rights required for any use of the Work.
|
|
110
|
+
|
|
111
|
+
d. Affirmer understands and acknowledges that Creative Commons is not a
|
|
112
|
+
party to this document and has no duty or obligation with respect to this
|
|
113
|
+
CC0 or use of the Work.
|
|
114
|
+
|
|
115
|
+
For more information, please see
|
|
116
|
+
<http://creativecommons.org/publicdomain/zero/1.0/>
|
data/README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
1
|
+
# WikiroFS
|
|
2
|
+
|
|
3
|
+
Wikiro is a virtual filesystem designed to mount Wikipedia in your filesystem.
|
|
4
|
+
|
|
5
|
+
## Installation
|
|
6
|
+
|
|
7
|
+
```bash
|
|
8
|
+
> sudo su
|
|
9
|
+
> gem install wikirofs
|
|
10
|
+
```
|
|
11
|
+
|
|
12
|
+
## Usage
|
|
13
|
+
```bash
|
|
14
|
+
# mount (eg. in /mnt/test)
|
|
15
|
+
> mount.wikiro /mnt/test
|
|
16
|
+
|
|
17
|
+
# default wikis
|
|
18
|
+
> ls /mnt/test
|
|
19
|
+
wikipedia-ceb
|
|
20
|
+
wikipedia-de
|
|
21
|
+
wikipedia-en
|
|
22
|
+
wikipedia-es
|
|
23
|
+
...
|
|
24
|
+
|
|
25
|
+
# main articles
|
|
26
|
+
> ls /mnt/test/wikipedia-en
|
|
27
|
+
Abacus.txt
|
|
28
|
+
Abiogenesis.txt
|
|
29
|
+
Abolitionism.txt
|
|
30
|
+
Abortion.txt
|
|
31
|
+
...
|
|
32
|
+
|
|
33
|
+
# not listed wikis
|
|
34
|
+
> mkdir /mnt/test/wikipedia-simple
|
|
35
|
+
> ls /mnt/test/wikipedia-simple
|
|
36
|
+
Abraham_Lincoln.txt
|
|
37
|
+
Acceleration.txt
|
|
38
|
+
Acid.txt
|
|
39
|
+
Adam_Smith.txt
|
|
40
|
+
...
|
|
41
|
+
|
|
42
|
+
# view article (even if it's not listed)
|
|
43
|
+
> cat /mnt/test/wikipedia-en/Moon.txt
|
|
44
|
+
{{about |Earths natural satellite |moons in general |Natural satellite |other uses}}
|
|
45
|
+
{{pp-semi-protected |small=yes}}
|
|
46
|
+
{{pp-move-indef}}
|
|
47
|
+
{{Use dmy dates|date=January 2017}}
|
|
48
|
+
...
|
|
49
|
+
|
|
50
|
+
# remove a wiki from the list (it doesn't affect the real Wikipedia)
|
|
51
|
+
> rmdir /mnt/test/wikipedia-ceb
|
|
52
|
+
> ls /mnt/test
|
|
53
|
+
wikipedia-ceb
|
|
54
|
+
wikipedia-de
|
|
55
|
+
wikipedia-en
|
|
56
|
+
...
|
|
57
|
+
|
|
58
|
+
# remove article from the list (it doesn't affect the real Wikipedia)
|
|
59
|
+
> rm /mnt/test/wikipedia-en/Abacus.txt
|
|
60
|
+
> ls /mnt/test/wikipedia-en
|
|
61
|
+
Abiogenesis.txt
|
|
62
|
+
Abolitionism.txt
|
|
63
|
+
Abortion.txt
|
|
64
|
+
...
|
|
65
|
+
|
|
66
|
+
# umount
|
|
67
|
+
> sudo umount /mnt/test
|
|
68
|
+
```
|
|
69
|
+
|
|
70
|
+
<!-- ## Mounting on boot
|
|
71
|
+
1. edit your /etc/fstab
|
|
72
|
+
2. add something like this:
|
|
73
|
+
```
|
|
74
|
+
/usr/sbin/mount.wikiro /mnt/test fuse user,noauto 0 0
|
|
75
|
+
```
|
|
76
|
+
-->
|
|
77
|
+
## Contributing
|
|
78
|
+
|
|
79
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/loureirorg/wikirofs.
|
data/Rakefile
ADDED
data/bin/console
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
1
|
+
#!/usr/bin/env ruby
|
|
2
|
+
|
|
3
|
+
require "bundler/setup"
|
|
4
|
+
require "wikirofs"
|
|
5
|
+
|
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
|
8
|
+
|
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
|
10
|
+
# require "pry"
|
|
11
|
+
# Pry.start
|
|
12
|
+
|
|
13
|
+
require "irb"
|
|
14
|
+
IRB.start(__FILE__)
|
data/bin/mount.wikiro
ADDED
|
@@ -0,0 +1 @@
|
|
|
1
|
+
../main.rb
|
data/bin/setup
ADDED
data/lib/wikipedia.rb
ADDED
|
@@ -0,0 +1,123 @@
|
|
|
1
|
+
class WikiReader
|
|
2
|
+
# Libraries
|
|
3
|
+
require 'openssl'
|
|
4
|
+
require 'httpclient'
|
|
5
|
+
require 'nokogiri'
|
|
6
|
+
|
|
7
|
+
# HTTP
|
|
8
|
+
@@http = HTTPClient.new
|
|
9
|
+
|
|
10
|
+
# Our database
|
|
11
|
+
# Format: @db = {'en' => ['link_a', 'link_b', ...], 'pt' => ['link_c', ...]}
|
|
12
|
+
# A language with a "nil" value means it wasn't initialized yet and we should
|
|
13
|
+
# call fetch_vital before use it
|
|
14
|
+
@@db = nil
|
|
15
|
+
@@sizes = {}
|
|
16
|
+
|
|
17
|
+
# all articles in memory
|
|
18
|
+
def self.articles(language = 'en')
|
|
19
|
+
return nil if ! db.key?(language) # invalid language
|
|
20
|
+
db[language] = fetch_vital(language) if ! db[language] # not initialized
|
|
21
|
+
|
|
22
|
+
db[language]
|
|
23
|
+
end
|
|
24
|
+
|
|
25
|
+
def self.languages
|
|
26
|
+
db.keys
|
|
27
|
+
end
|
|
28
|
+
|
|
29
|
+
def self.article(title, language = 'en')
|
|
30
|
+
raise Errno::ENOENT if ! db.key?(language) # invalid language
|
|
31
|
+
db[language] = fetch_vital(language) if ! db[language] # not initialized
|
|
32
|
+
|
|
33
|
+
art = fetch_article(title, language) # read from the internet
|
|
34
|
+
raise Errno::ENOENT if ! art
|
|
35
|
+
db[language] << title if art && ! db[language].index(title) # adds in our list
|
|
36
|
+
|
|
37
|
+
@@sizes[language] ||= {}
|
|
38
|
+
@@sizes[language][title] = art.bytesize
|
|
39
|
+
|
|
40
|
+
art
|
|
41
|
+
end
|
|
42
|
+
|
|
43
|
+
def self.size(title, language = 'en')
|
|
44
|
+
@@sizes[language] ||= {}
|
|
45
|
+
@@sizes[language][title] || 1
|
|
46
|
+
end
|
|
47
|
+
|
|
48
|
+
def self.db
|
|
49
|
+
return @@db if @@db
|
|
50
|
+
@@db = Hash[fetch_languages.collect { |item| [item, nil] }]
|
|
51
|
+
end
|
|
52
|
+
|
|
53
|
+
private
|
|
54
|
+
|
|
55
|
+
def self.fetch_article(title, language = 'en')
|
|
56
|
+
begin
|
|
57
|
+
url = "https://#{language}.wikipedia.org/wiki/#{URI::encode(title)}?action=raw"
|
|
58
|
+
@@http.get_content(url)
|
|
59
|
+
rescue => e
|
|
60
|
+
puts e
|
|
61
|
+
nil
|
|
62
|
+
end
|
|
63
|
+
end
|
|
64
|
+
|
|
65
|
+
def self.fetch_languages
|
|
66
|
+
# hardcoded list (used as fallback)
|
|
67
|
+
default = [
|
|
68
|
+
'en', 'ceb', 'sv', 'de', 'nl', 'fr', 'ru', 'it', 'es', 'war', 'pl', 'vi',
|
|
69
|
+
'ja', 'pt', 'zh', 'uk', 'ca', 'fa', 'ar', 'no', 'sh', 'fi', 'hu', 'id',
|
|
70
|
+
'cs', 'ko', 'ro', 'sr', 'tr', 'ms', 'eu', 'eo', 'bg', 'da', 'min', 'kk',
|
|
71
|
+
'hy', 'sk', 'zh-min-nan', 'he', 'lt', 'hr', 'ce', 'et', 'sl', 'be', 'gl',
|
|
72
|
+
'nn', 'el', 'uz', 'la', 'simple', 'vo', 'ur', 'hi', 'az', 'th', 'ka'
|
|
73
|
+
]
|
|
74
|
+
|
|
75
|
+
# fetch from the internet
|
|
76
|
+
lst = nil
|
|
77
|
+
begin
|
|
78
|
+
url = 'https://meta.wikimedia.org/wiki/List_of_Wikipedias'
|
|
79
|
+
doc = Nokogiri::HTML(@@http.get_content(url))
|
|
80
|
+
lst = doc.at_css('[id="1_000_000.2B_articles"]').xpath('./ancestor::h3')[0].next.next.children.xpath('td[4]').map {|e| e.text}
|
|
81
|
+
lst += doc.at_css('[id="100_000.2B_articles"]').xpath('./ancestor::h3')[0].next.next.children.xpath('td[4]').map {|e| e.text}
|
|
82
|
+
rescue
|
|
83
|
+
end
|
|
84
|
+
|
|
85
|
+
# uses default list if theres no results
|
|
86
|
+
lst = (lst.class == Array) && lst.any? ? lst : default
|
|
87
|
+
lst[0, 15]
|
|
88
|
+
end
|
|
89
|
+
|
|
90
|
+
def self.fetch_vital(language = 'en')
|
|
91
|
+
lst = []
|
|
92
|
+
|
|
93
|
+
begin
|
|
94
|
+
url = 'https://en.wikipedia.org/wiki/Wikipedia:Vital_articles'
|
|
95
|
+
doc = Nokogiri::HTML(@@http.get_content(url))
|
|
96
|
+
|
|
97
|
+
# not english, click on "Languages" section (left column)
|
|
98
|
+
if language != 'en'
|
|
99
|
+
link = doc.at_css("a.interlanguage-link-target[lang='#{language}']")
|
|
100
|
+
return [] if ! link
|
|
101
|
+
url = link.attribute('href')
|
|
102
|
+
doc = Nokogiri::HTML(@@http.get_content(url))
|
|
103
|
+
return [] if ! doc
|
|
104
|
+
end
|
|
105
|
+
|
|
106
|
+
# get all links starting with "/wiki/" and with no class (it will get some extra non-vital articles, but it's ok)
|
|
107
|
+
lst = doc.xpath('//li/a[not (@class)][starts-with(@href, "/wiki/")]').map do |e|
|
|
108
|
+
href = e.attribute('href').text[6..-1] # remove initial '/wiki/'
|
|
109
|
+
href = URI::decode(href) # convert non-ascii chars
|
|
110
|
+
pos = href.index('#')
|
|
111
|
+
href = href[0, href.index('#')] if pos # remove anchor
|
|
112
|
+
href
|
|
113
|
+
end
|
|
114
|
+
|
|
115
|
+
lst.uniq!
|
|
116
|
+
|
|
117
|
+
rescue
|
|
118
|
+
end # rescue
|
|
119
|
+
|
|
120
|
+
lst
|
|
121
|
+
end
|
|
122
|
+
|
|
123
|
+
end
|
data/lib/wikirofs.rb
ADDED
data/main.rb
ADDED
|
@@ -0,0 +1,176 @@
|
|
|
1
|
+
#!/usr/bin/env ruby
|
|
2
|
+
require 'rfusefs'
|
|
3
|
+
require './wikipedia.rb'
|
|
4
|
+
|
|
5
|
+
class WikiNgFS
|
|
6
|
+
class WikiFileHandle
|
|
7
|
+
attr_accessor :contents, :title, :language
|
|
8
|
+
|
|
9
|
+
def initialize(title, language)
|
|
10
|
+
@title = title
|
|
11
|
+
@language = language
|
|
12
|
+
end
|
|
13
|
+
end
|
|
14
|
+
|
|
15
|
+
def touch(path, modtime = nil)
|
|
16
|
+
# puts "touch #{path}"
|
|
17
|
+
modtime = Time.now.to_i if ! modtime
|
|
18
|
+
language, title = parse_path(path)
|
|
19
|
+
raise Errno::EPERM if ! language if ! title
|
|
20
|
+
articles = WikiReader.articles(language)
|
|
21
|
+
articles << title if articles && ! articles.include?(title)
|
|
22
|
+
end
|
|
23
|
+
|
|
24
|
+
def can_delete?(path)
|
|
25
|
+
# puts "can_delete? #{path}"
|
|
26
|
+
language, title = parse_path(path)
|
|
27
|
+
articles = WikiReader.articles(language)
|
|
28
|
+
title && articles && articles.include?(title)
|
|
29
|
+
end
|
|
30
|
+
|
|
31
|
+
def delete(path)
|
|
32
|
+
# puts "delete #{path}"
|
|
33
|
+
language, title = parse_path(path)
|
|
34
|
+
WikiReader.articles(language).delete(title)
|
|
35
|
+
end
|
|
36
|
+
|
|
37
|
+
def can_mkdir?(path)
|
|
38
|
+
# puts "can_mkdir? #{path}"
|
|
39
|
+
language, title = parse_path(path)
|
|
40
|
+
language && ! title
|
|
41
|
+
end
|
|
42
|
+
|
|
43
|
+
def mkdir(path)
|
|
44
|
+
# puts "mkdir #{path}"
|
|
45
|
+
language, title = parse_path(path)
|
|
46
|
+
WikiReader.db[language] = nil
|
|
47
|
+
end
|
|
48
|
+
|
|
49
|
+
def can_rmdir?(path)
|
|
50
|
+
# puts "can_mkdir? #{path}"
|
|
51
|
+
language, title = parse_path(path)
|
|
52
|
+
language && ! title
|
|
53
|
+
end
|
|
54
|
+
|
|
55
|
+
def rmdir(path)
|
|
56
|
+
# puts "rmdir #{path}"
|
|
57
|
+
language, title = parse_path(path)
|
|
58
|
+
WikiReader.db.delete(language)
|
|
59
|
+
end
|
|
60
|
+
|
|
61
|
+
|
|
62
|
+
def contents(path)
|
|
63
|
+
# puts "contents #{path}"
|
|
64
|
+
if path == '/'
|
|
65
|
+
# adds 'wikipedia-' at beginning
|
|
66
|
+
lst = WikiReader.languages.dup
|
|
67
|
+
lst.each_with_index {|v, i| lst[i] = "wikipedia-#{v}"}
|
|
68
|
+
return lst
|
|
69
|
+
|
|
70
|
+
else
|
|
71
|
+
language, title = parse_path(path)
|
|
72
|
+
return nil if ! language && ! title # invalid language and title
|
|
73
|
+
|
|
74
|
+
if language && ! title # eg: "ls /wikipedia-en"
|
|
75
|
+
lst = WikiReader.articles(language).dup.sort
|
|
76
|
+
lst.each_with_index {|v, i| lst[i] = "#{v}.txt"}
|
|
77
|
+
lst.each {|v| v.gsub!(/^.*(\\|\/)/, '')} # "/" -> "\/"
|
|
78
|
+
return lst
|
|
79
|
+
end
|
|
80
|
+
return [title]
|
|
81
|
+
end
|
|
82
|
+
end
|
|
83
|
+
|
|
84
|
+
def file?(path)
|
|
85
|
+
# puts "file? #{path}"
|
|
86
|
+
language, title = parse_path(path)
|
|
87
|
+
!!(language && title)
|
|
88
|
+
end
|
|
89
|
+
|
|
90
|
+
def directory?(path)
|
|
91
|
+
# puts "directory? #{path}"
|
|
92
|
+
language, title = parse_path(path)
|
|
93
|
+
language = nil if language && ! WikiReader.languages.include?(language)
|
|
94
|
+
!!(language && !title)
|
|
95
|
+
end
|
|
96
|
+
|
|
97
|
+
def can_write?(path)
|
|
98
|
+
# puts "can_write? #{path}"
|
|
99
|
+
false
|
|
100
|
+
end
|
|
101
|
+
|
|
102
|
+
def rename(from_path, to_path)
|
|
103
|
+
# puts "rename #{path}"
|
|
104
|
+
delete(from_path)
|
|
105
|
+
touch(to_path)
|
|
106
|
+
end
|
|
107
|
+
|
|
108
|
+
def size(path)
|
|
109
|
+
# puts "size #{path}"
|
|
110
|
+
language, title = parse_path(path)
|
|
111
|
+
WikiReader.size(title, language)
|
|
112
|
+
end
|
|
113
|
+
|
|
114
|
+
# def read_file(path)
|
|
115
|
+
# language, title = parse_path(path)
|
|
116
|
+
# raise Errno::ENOENT if ! language || ! title
|
|
117
|
+
# end
|
|
118
|
+
|
|
119
|
+
def raw_open(path, mode, rfusefs = nil)
|
|
120
|
+
# puts "raw_open #{path}"
|
|
121
|
+
language, title = parse_path(path)
|
|
122
|
+
raise Errno::ENOENT if ! language || ! title
|
|
123
|
+
WikiFileHandle.new(title, language)
|
|
124
|
+
end
|
|
125
|
+
|
|
126
|
+
def raw_read(path, offset, size, handler = nil)
|
|
127
|
+
# puts "raw_read #{path}"
|
|
128
|
+
raise Errno::EBADF if ! handler
|
|
129
|
+
handler.contents ||= WikiReader.article(handler.title, handler.language)
|
|
130
|
+
handler.contents.b[offset, size]
|
|
131
|
+
end
|
|
132
|
+
|
|
133
|
+
def raw_close(path, handler = nil)
|
|
134
|
+
# puts "raw_close #{path}"
|
|
135
|
+
raise Errno::EBADF if ! handler
|
|
136
|
+
handler.contents = nil
|
|
137
|
+
end
|
|
138
|
+
|
|
139
|
+
private
|
|
140
|
+
|
|
141
|
+
def parse_path(path)
|
|
142
|
+
#######################
|
|
143
|
+
# PATH FORMAT:
|
|
144
|
+
# /wikipedia-<language>/<title>.txt
|
|
145
|
+
#######################
|
|
146
|
+
|
|
147
|
+
# break items: '/wikipedia-en/Titanic.txt' -> ['', 'wikipedia-en', 'Titanic'] -> ['wikipedia-en', 'Titanic']
|
|
148
|
+
items = path.split(File::SEPARATOR)
|
|
149
|
+
items.shift if items.first == ''
|
|
150
|
+
return nil if items.empty? || (items.count > 2)
|
|
151
|
+
|
|
152
|
+
# language: 'wikipedia-en' -> 'en'
|
|
153
|
+
pos = items[0].index('wikipedia-')
|
|
154
|
+
return nil if ! pos || (items[0] == 'wikipedia-')
|
|
155
|
+
language = items[0][pos+10..-1]
|
|
156
|
+
|
|
157
|
+
# title
|
|
158
|
+
title = nil
|
|
159
|
+
if items[1]
|
|
160
|
+
pos = items[1].index('.txt')
|
|
161
|
+
language = nil if ! pos # invalid file extension
|
|
162
|
+
title = items[1][0, pos] if pos
|
|
163
|
+
end
|
|
164
|
+
|
|
165
|
+
# result
|
|
166
|
+
[language, title]
|
|
167
|
+
end
|
|
168
|
+
end
|
|
169
|
+
|
|
170
|
+
# @opts = *ARGV[1..-1]
|
|
171
|
+
# FuseFS.mount(WikiNgFS.new, ARGV[0], @opts)
|
|
172
|
+
# FuseFS.mount(WikiNgFS.new, ARGV[0])
|
|
173
|
+
|
|
174
|
+
# wikifs = WikiNgFS.new
|
|
175
|
+
# FuseFS.start(wikifs, '/mnt/test')
|
|
176
|
+
FuseFS.main() { |options| WikiNgFS.new }
|
data/wikirofs.gemspec
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
1
|
+
# coding: utf-8
|
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
|
4
|
+
require 'wikirofs/version'
|
|
5
|
+
|
|
6
|
+
Gem::Specification.new do |spec|
|
|
7
|
+
spec.name = "wikirofs"
|
|
8
|
+
spec.version = Wikirofs::VERSION
|
|
9
|
+
spec.authors = ["Daniel Loureiro"]
|
|
10
|
+
spec.email = ["loureirorg@gmail.com"]
|
|
11
|
+
spec.licenses = ['CC0-1.0']
|
|
12
|
+
|
|
13
|
+
spec.summary = %q{Wikipedia Virtual FileSystem (read-only)}
|
|
14
|
+
spec.description = %q{A virtual filesystem to mount wikipedia.}
|
|
15
|
+
spec.homepage = "http://www.learnwithdaniel.com"
|
|
16
|
+
|
|
17
|
+
spec.files = `git ls-files -z`.split("\x0").reject do |f|
|
|
18
|
+
f.match(%r{^(test|spec|features)/})
|
|
19
|
+
end
|
|
20
|
+
spec.bindir = "bin"
|
|
21
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
|
22
|
+
spec.require_paths = ["lib"]
|
|
23
|
+
spec.executables << 'mount.wikiro'
|
|
24
|
+
|
|
25
|
+
spec.add_development_dependency "bundler", "~> 1.14"
|
|
26
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
|
27
|
+
spec.add_runtime_dependency "nokogiri", "~> 1.7"
|
|
28
|
+
spec.add_runtime_dependency "rfusefs", "~> 1.0"
|
|
29
|
+
spec.add_runtime_dependency "httpclient", "~> 2.8"
|
|
30
|
+
end
|
metadata
ADDED
|
@@ -0,0 +1,128 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: wikirofs
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.1.0
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- Daniel Loureiro
|
|
8
|
+
autorequire:
|
|
9
|
+
bindir: bin
|
|
10
|
+
cert_chain: []
|
|
11
|
+
date: 2017-04-05 00:00:00.000000000 Z
|
|
12
|
+
dependencies:
|
|
13
|
+
- !ruby/object:Gem::Dependency
|
|
14
|
+
name: bundler
|
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
|
16
|
+
requirements:
|
|
17
|
+
- - "~>"
|
|
18
|
+
- !ruby/object:Gem::Version
|
|
19
|
+
version: '1.14'
|
|
20
|
+
type: :development
|
|
21
|
+
prerelease: false
|
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
23
|
+
requirements:
|
|
24
|
+
- - "~>"
|
|
25
|
+
- !ruby/object:Gem::Version
|
|
26
|
+
version: '1.14'
|
|
27
|
+
- !ruby/object:Gem::Dependency
|
|
28
|
+
name: rake
|
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
|
30
|
+
requirements:
|
|
31
|
+
- - "~>"
|
|
32
|
+
- !ruby/object:Gem::Version
|
|
33
|
+
version: '10.0'
|
|
34
|
+
type: :development
|
|
35
|
+
prerelease: false
|
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
37
|
+
requirements:
|
|
38
|
+
- - "~>"
|
|
39
|
+
- !ruby/object:Gem::Version
|
|
40
|
+
version: '10.0'
|
|
41
|
+
- !ruby/object:Gem::Dependency
|
|
42
|
+
name: nokogiri
|
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
|
44
|
+
requirements:
|
|
45
|
+
- - "~>"
|
|
46
|
+
- !ruby/object:Gem::Version
|
|
47
|
+
version: '1.7'
|
|
48
|
+
type: :runtime
|
|
49
|
+
prerelease: false
|
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
51
|
+
requirements:
|
|
52
|
+
- - "~>"
|
|
53
|
+
- !ruby/object:Gem::Version
|
|
54
|
+
version: '1.7'
|
|
55
|
+
- !ruby/object:Gem::Dependency
|
|
56
|
+
name: rfusefs
|
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
|
58
|
+
requirements:
|
|
59
|
+
- - "~>"
|
|
60
|
+
- !ruby/object:Gem::Version
|
|
61
|
+
version: '1.0'
|
|
62
|
+
type: :runtime
|
|
63
|
+
prerelease: false
|
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
65
|
+
requirements:
|
|
66
|
+
- - "~>"
|
|
67
|
+
- !ruby/object:Gem::Version
|
|
68
|
+
version: '1.0'
|
|
69
|
+
- !ruby/object:Gem::Dependency
|
|
70
|
+
name: httpclient
|
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
|
72
|
+
requirements:
|
|
73
|
+
- - "~>"
|
|
74
|
+
- !ruby/object:Gem::Version
|
|
75
|
+
version: '2.8'
|
|
76
|
+
type: :runtime
|
|
77
|
+
prerelease: false
|
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
79
|
+
requirements:
|
|
80
|
+
- - "~>"
|
|
81
|
+
- !ruby/object:Gem::Version
|
|
82
|
+
version: '2.8'
|
|
83
|
+
description: A virtual filesystem to mount wikipedia.
|
|
84
|
+
email:
|
|
85
|
+
- loureirorg@gmail.com
|
|
86
|
+
executables:
|
|
87
|
+
- mount.wikiro
|
|
88
|
+
extensions: []
|
|
89
|
+
extra_rdoc_files: []
|
|
90
|
+
files:
|
|
91
|
+
- ".gitignore"
|
|
92
|
+
- Gemfile
|
|
93
|
+
- LICENSE
|
|
94
|
+
- README.md
|
|
95
|
+
- Rakefile
|
|
96
|
+
- bin/console
|
|
97
|
+
- bin/mount.wikiro
|
|
98
|
+
- bin/setup
|
|
99
|
+
- lib/wikipedia.rb
|
|
100
|
+
- lib/wikirofs.rb
|
|
101
|
+
- lib/wikirofs/version.rb
|
|
102
|
+
- main.rb
|
|
103
|
+
- wikirofs.gemspec
|
|
104
|
+
homepage: http://www.learnwithdaniel.com
|
|
105
|
+
licenses:
|
|
106
|
+
- CC0-1.0
|
|
107
|
+
metadata: {}
|
|
108
|
+
post_install_message:
|
|
109
|
+
rdoc_options: []
|
|
110
|
+
require_paths:
|
|
111
|
+
- lib
|
|
112
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
113
|
+
requirements:
|
|
114
|
+
- - ">="
|
|
115
|
+
- !ruby/object:Gem::Version
|
|
116
|
+
version: '0'
|
|
117
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
118
|
+
requirements:
|
|
119
|
+
- - ">="
|
|
120
|
+
- !ruby/object:Gem::Version
|
|
121
|
+
version: '0'
|
|
122
|
+
requirements: []
|
|
123
|
+
rubyforge_project:
|
|
124
|
+
rubygems_version: 2.5.1
|
|
125
|
+
signing_key:
|
|
126
|
+
specification_version: 4
|
|
127
|
+
summary: Wikipedia Virtual FileSystem (read-only)
|
|
128
|
+
test_files: []
|