plainwiki 0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/lib/parser.rb +244 -0
- data/lib/plainwiki.rb +1 -0
- metadata +45 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 63e74a0a4695347315a0666c485031f28e026779
|
4
|
+
data.tar.gz: e056e2d0d6e51a1acac87fe32d832b49c11c2135
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 4e4985d439e731059d1d5e7db8507701856911a401560c7a127fad71abcbcfd2cbba5b6b5b25a742a1a6e30c3b97b1616e7839e8d87b61f1612a01c905ee285c
|
7
|
+
data.tar.gz: fd18271df53de21495be12406048b69151aa237b0688253ee0800f1659e4cad8f508412289cda0c0822bf10641c383d2da9f3c6878f1bde068dba10f5b587d9d
|
data/lib/parser.rb
ADDED
@@ -0,0 +1,244 @@
|
|
1
|
+
module PlainWiki
|
2
|
+
class Parser
|
3
|
+
def self.parse wikitext
|
4
|
+
ps = "detect"
|
5
|
+
out = ""
|
6
|
+
helper = ""
|
7
|
+
linkhelper = ""
|
8
|
+
toparse = ""
|
9
|
+
linktext = false
|
10
|
+
intlinkpiped = false
|
11
|
+
speciallev = 0
|
12
|
+
wikitext.each_char do |c|
|
13
|
+
case ps
|
14
|
+
when "detect"
|
15
|
+
if c == "'"
|
16
|
+
next
|
17
|
+
elsif c == "<"
|
18
|
+
ps = "markup"
|
19
|
+
elsif c == "["
|
20
|
+
ps = "link"
|
21
|
+
elsif c == "]"
|
22
|
+
next
|
23
|
+
elsif c == "{"
|
24
|
+
ps = "tabledetect"
|
25
|
+
else
|
26
|
+
out += c
|
27
|
+
end
|
28
|
+
when "markup"
|
29
|
+
if c == ">"
|
30
|
+
if helper == "strike"
|
31
|
+
ps = "strike"
|
32
|
+
elsif helper == "nowiki/" || helper == "nowiki /"
|
33
|
+
ps = "detect"
|
34
|
+
elsif helper == "nowiki"
|
35
|
+
ps = "nowiki"
|
36
|
+
elsif helper == "ins" || helper == "u"
|
37
|
+
ps = "underline"
|
38
|
+
elsif helper == "s" || helper == "del"
|
39
|
+
ps = "strike"
|
40
|
+
elsif helper == "code" || helper == "tt" || helper == "pre"
|
41
|
+
ps = "nowiki"
|
42
|
+
elsif helper == "blockquote"
|
43
|
+
ps = "blockquote"
|
44
|
+
elsif helper == "br" || helper == "br /"
|
45
|
+
out += "/n"
|
46
|
+
ps = "detect"
|
47
|
+
elsif helper.include?("!--")
|
48
|
+
ps = "detect"
|
49
|
+
elsif helper.match(/ref .*\//) != nil
|
50
|
+
ps = "detect"
|
51
|
+
elsif helper.match(/ref .*/) != nil
|
52
|
+
ps = "ref"
|
53
|
+
else
|
54
|
+
ps = "detect"
|
55
|
+
end
|
56
|
+
helper = ""
|
57
|
+
else
|
58
|
+
helper += c
|
59
|
+
end
|
60
|
+
when "strike"
|
61
|
+
if c == "<"
|
62
|
+
ps = "strikeend"
|
63
|
+
else
|
64
|
+
toparse += c
|
65
|
+
end
|
66
|
+
when "strikeend"
|
67
|
+
if c == ">"
|
68
|
+
if helper == "/strike" || helper == "/s" || helper == "/del"
|
69
|
+
out += self.parse(toparse)
|
70
|
+
toparse = ""
|
71
|
+
helper = ""
|
72
|
+
ps = "detect"
|
73
|
+
else
|
74
|
+
toparse += "<"
|
75
|
+
toparse += helper
|
76
|
+
toparse += ">"
|
77
|
+
ps = "strike"
|
78
|
+
end
|
79
|
+
helper = ""
|
80
|
+
else
|
81
|
+
helper += c
|
82
|
+
end
|
83
|
+
when "underline"
|
84
|
+
if c == "<"
|
85
|
+
ps = "underlineend"
|
86
|
+
else
|
87
|
+
toparse += c
|
88
|
+
end
|
89
|
+
when "underlineend"
|
90
|
+
if c == ">"
|
91
|
+
if helper == "/u" || helper == "/ins"
|
92
|
+
out += self.parse(toparse)
|
93
|
+
toparse = ""
|
94
|
+
helper = ""
|
95
|
+
ps = "detect"
|
96
|
+
else
|
97
|
+
toparse += "<"
|
98
|
+
toparse += helper
|
99
|
+
toparse += ">"
|
100
|
+
ps = "strike"
|
101
|
+
end
|
102
|
+
helper = ""
|
103
|
+
else
|
104
|
+
helper += c
|
105
|
+
end
|
106
|
+
when "nowiki"
|
107
|
+
if c == "<"
|
108
|
+
ps = "nowikiend"
|
109
|
+
else
|
110
|
+
out += c
|
111
|
+
end
|
112
|
+
when "nowikiend"
|
113
|
+
if c == ">"
|
114
|
+
if helper == "/nowiki" || helper == "/code" || helper == "/tt" || helper == "/pre"
|
115
|
+
helper = ""
|
116
|
+
ps = "detect"
|
117
|
+
else
|
118
|
+
out += "<"
|
119
|
+
out += helper
|
120
|
+
out += ">"
|
121
|
+
ps = "nowiki"
|
122
|
+
end
|
123
|
+
helper = ""
|
124
|
+
else
|
125
|
+
helper += c
|
126
|
+
end
|
127
|
+
when "ref"
|
128
|
+
if c == "<"
|
129
|
+
ps = "refend"
|
130
|
+
end
|
131
|
+
when "refend"
|
132
|
+
if c == ">"
|
133
|
+
if helper == "/ref"
|
134
|
+
helper = ""
|
135
|
+
ps = "detect"
|
136
|
+
else
|
137
|
+
ps = "ref"
|
138
|
+
end
|
139
|
+
else
|
140
|
+
helper += c
|
141
|
+
end
|
142
|
+
when "link"
|
143
|
+
if c == "["
|
144
|
+
ps = "intlink"
|
145
|
+
elsif c == "]"
|
146
|
+
linktext = false
|
147
|
+
out += linkhelper
|
148
|
+
out += " "
|
149
|
+
out += helper
|
150
|
+
linkhelper = ""
|
151
|
+
helper = ""
|
152
|
+
ps = "detect"
|
153
|
+
elsif c == " " && !linktext
|
154
|
+
linktext = true
|
155
|
+
else
|
156
|
+
if !linktext
|
157
|
+
linkhelper += c
|
158
|
+
else
|
159
|
+
helper += c
|
160
|
+
end
|
161
|
+
end
|
162
|
+
when "intlink"
|
163
|
+
if c == "]"
|
164
|
+
ps = "intlinkend"
|
165
|
+
elsif c == "|"
|
166
|
+
intlinkpiped = true
|
167
|
+
else
|
168
|
+
if !intlinkpiped
|
169
|
+
linkhelper += c
|
170
|
+
else
|
171
|
+
helper += c
|
172
|
+
end
|
173
|
+
end
|
174
|
+
when "intlinkend"
|
175
|
+
if c == "]"
|
176
|
+
if !["Kategoria", "Category", "Plik", "File"].include?(linkhelper.split(":").first)
|
177
|
+
if intlinkpiped
|
178
|
+
if helper == ""
|
179
|
+
hout = ""
|
180
|
+
helper.split(":").last.split(" ").each do |s|
|
181
|
+
if s.match(/\(.*\)/) == nil
|
182
|
+
hout += " "
|
183
|
+
hout += s
|
184
|
+
else
|
185
|
+
next
|
186
|
+
end
|
187
|
+
end
|
188
|
+
hout.strip!
|
189
|
+
out += hout
|
190
|
+
else
|
191
|
+
out += helper
|
192
|
+
end
|
193
|
+
else
|
194
|
+
out += linkhelper
|
195
|
+
end
|
196
|
+
end
|
197
|
+
linkhelper = ""
|
198
|
+
helper = ""
|
199
|
+
intlinkpiped = false
|
200
|
+
ps = "detect"
|
201
|
+
else
|
202
|
+
if !intlinkpiped
|
203
|
+
linkhelper += "]"
|
204
|
+
linkhelper += c
|
205
|
+
else
|
206
|
+
helper += "]"
|
207
|
+
helper += c
|
208
|
+
end
|
209
|
+
end
|
210
|
+
when "tabledetect"
|
211
|
+
if c == "|"
|
212
|
+
ps = "table"
|
213
|
+
elsif c == "{"
|
214
|
+
ps = "special"
|
215
|
+
speciallev += 1
|
216
|
+
end
|
217
|
+
when "table"
|
218
|
+
ps = "special"
|
219
|
+
speciallev += 1
|
220
|
+
when "special"
|
221
|
+
if c == "}"
|
222
|
+
ps = "specialend"
|
223
|
+
elsif c == "{"
|
224
|
+
ps = "tabledetect"
|
225
|
+
end
|
226
|
+
when "specialend"
|
227
|
+
if c == "}"
|
228
|
+
speciallev -= 1
|
229
|
+
if speciallev == 0
|
230
|
+
ps = "detect"
|
231
|
+
else
|
232
|
+
ps = "special"
|
233
|
+
end
|
234
|
+
else
|
235
|
+
ps = "special"
|
236
|
+
end
|
237
|
+
else
|
238
|
+
ps = "detect"
|
239
|
+
end
|
240
|
+
end
|
241
|
+
out.strip
|
242
|
+
end
|
243
|
+
end
|
244
|
+
end
|
data/lib/plainwiki.rb
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require 'parser'
|
metadata
ADDED
@@ -0,0 +1,45 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: plainwiki
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: '0.1'
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Phitherek_
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-02-27 00:00:00.000000000 Z
|
12
|
+
dependencies: []
|
13
|
+
description: This gem provides a parser that strips out MediaWiki' s wikitext to plain
|
14
|
+
text. Not affliated with Wikimedia or MediaWiki in any way.
|
15
|
+
email: phitherek@gmail.com
|
16
|
+
executables: []
|
17
|
+
extensions: []
|
18
|
+
extra_rdoc_files: []
|
19
|
+
files:
|
20
|
+
- lib/parser.rb
|
21
|
+
- lib/plainwiki.rb
|
22
|
+
homepage: https://github.com/Phitherek/plainwiki
|
23
|
+
licenses: []
|
24
|
+
metadata: {}
|
25
|
+
post_install_message:
|
26
|
+
rdoc_options: []
|
27
|
+
require_paths:
|
28
|
+
- lib
|
29
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
35
|
+
requirements:
|
36
|
+
- - ">="
|
37
|
+
- !ruby/object:Gem::Version
|
38
|
+
version: '0'
|
39
|
+
requirements: []
|
40
|
+
rubyforge_project:
|
41
|
+
rubygems_version: 2.2.2
|
42
|
+
signing_key:
|
43
|
+
specification_version: 4
|
44
|
+
summary: A MediaWiki wikitext to plain text parser gem
|
45
|
+
test_files: []
|