wikitext 0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/ext/ary.h +99 -0
- data/ext/depend +22 -0
- data/ext/extconf.rb +23 -0
- data/ext/parser.c +2174 -0
- data/ext/parser.h +31 -0
- data/ext/str.h +135 -0
- data/ext/token.c +109 -0
- data/ext/token.h +95 -0
- data/ext/wikitext.c +60 -0
- data/ext/wikitext.h +30 -0
- data/ext/wikitext_ragel.c +3354 -0
- data/ext/wikitext_ragel.h +17 -0
- data/spec/autolinking_spec.rb +122 -0
- data/spec/blockquote_spec.rb +570 -0
- data/spec/em_spec.rb +97 -0
- data/spec/encoding_spec.rb +124 -0
- data/spec/entity_spec.rb +40 -0
- data/spec/external_link_spec.rb +289 -0
- data/spec/h1_spec.rb +59 -0
- data/spec/h2_spec.rb +59 -0
- data/spec/h3_spec.rb +59 -0
- data/spec/h4_spec.rb +59 -0
- data/spec/h5_spec.rb +59 -0
- data/spec/h6_spec.rb +59 -0
- data/spec/indentation_spec.rb +70 -0
- data/spec/integration_spec.rb +265 -0
- data/spec/internal_link_spec.rb +445 -0
- data/spec/line_endings_spec.rb +81 -0
- data/spec/link_encoding_spec.rb +132 -0
- data/spec/link_sanitizing_spec.rb +228 -0
- data/spec/nowiki_spec.rb +155 -0
- data/spec/p_spec.rb +44 -0
- data/spec/pre_spec.rb +411 -0
- data/spec/regressions_spec.rb +45 -0
- data/spec/spec_helper.rb +77 -0
- data/spec/strong_em_spec.rb +89 -0
- data/spec/strong_spec.rb +99 -0
- data/spec/tokenizing_spec.rb +190 -0
- data/spec/tt_spec.rb +100 -0
- data/spec/ul_spec.rb +307 -0
- data/spec/wikitext_spec.rb +50 -0
- metadata +93 -0
data/spec/tt_spec.rb
ADDED
@@ -0,0 +1,100 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
# Copyright 2007-2008 Wincent Colaiuta
|
3
|
+
# This program is free software: you can redistribute it and/or modify
|
4
|
+
# it under the terms of the GNU General Public License as published by
|
5
|
+
# the Free Software Foundation, either version 3 of the License, or
|
6
|
+
# (at your option) any later version.
|
7
|
+
#
|
8
|
+
# This program is distributed in the hope that it will be useful,
|
9
|
+
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
10
|
+
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
11
|
+
# GNU General Public License for more details.
|
12
|
+
#
|
13
|
+
# You should have received a copy of the GNU General Public License
|
14
|
+
# along with this program. If not, see <http://www.gnu.org/licenses/>.
|
15
|
+
|
16
|
+
require File.join(File.dirname(__FILE__), 'spec_helper.rb')
|
17
|
+
require 'wikitext'
|
18
|
+
|
19
|
+
describe Wikitext::Parser, 'parsing <tt> spans' do
|
20
|
+
before do
|
21
|
+
@parser = Wikitext::Parser.new
|
22
|
+
end
|
23
|
+
|
24
|
+
it 'should recognize paired <tt> and </tt> tags' do
|
25
|
+
@parser.parse('foo <tt>bar</tt> baz').should == "<p>foo <tt>bar</tt> baz</p>\n"
|
26
|
+
end
|
27
|
+
|
28
|
+
it 'should recognize <tt> tags case-insensitively' do
|
29
|
+
@parser.parse('foo <TT>bar</tT> baz').should == "<p>foo <tt>bar</tt> baz</p>\n"
|
30
|
+
@parser.parse('foo <tT>bar</Tt> baz').should == "<p>foo <tt>bar</tt> baz</p>\n"
|
31
|
+
@parser.parse('foo <Tt>bar</TT> baz').should == "<p>foo <tt>bar</tt> baz</p>\n"
|
32
|
+
end
|
33
|
+
|
34
|
+
it 'should automatically insert missing closing tags' do
|
35
|
+
@parser.parse('foo <tt>bar').should == "<p>foo <tt>bar</tt></p>\n"
|
36
|
+
end
|
37
|
+
|
38
|
+
it 'should automatically close unclosed spans upon hitting newline' do
|
39
|
+
@parser.parse("foo <tt>bar\nbaz").should == "<p>foo <tt>bar</tt> baz</p>\n"
|
40
|
+
end
|
41
|
+
|
42
|
+
it 'should convert unexpected closing tags into entities' do
|
43
|
+
@parser.parse('foo </tt>bar').should == "<p>foo </tt>bar</p>\n"
|
44
|
+
end
|
45
|
+
|
46
|
+
it 'should handle (illegal) nested <tt> spans' do
|
47
|
+
@parser.parse('foo <tt>bar <tt>inner</tt></tt> baz').should == "<p>foo <tt>bar <tt>inner</tt></tt> baz</p>\n"
|
48
|
+
end
|
49
|
+
|
50
|
+
it 'should handle (illegal) interleaved spans' do
|
51
|
+
@parser.parse("foo <tt>bar '''inner</tt> baz'''").should == "<p>foo <tt>bar <strong>inner</strong></tt> baz<strong></strong></p>\n"
|
52
|
+
end
|
53
|
+
|
54
|
+
it 'should have no effect inside <pre> blocks' do
|
55
|
+
@parser.parse(' <tt>foo</tt>').should == "<pre><tt>foo</tt></pre>\n"
|
56
|
+
end
|
57
|
+
|
58
|
+
it 'should have no effect inside <nowiki> spans' do
|
59
|
+
@parser.parse('<nowiki><tt>foo</tt></nowiki>').should == "<p><tt>foo</tt></p>\n"
|
60
|
+
end
|
61
|
+
|
62
|
+
it 'should have no effect if a backtick span is already open' do
|
63
|
+
@parser.parse('foo `<tt>bar</tt>` baz').should == "<p>foo <tt><tt>bar</tt></tt> baz</p>\n"
|
64
|
+
end
|
65
|
+
end
|
66
|
+
|
67
|
+
describe Wikitext::Parser, 'parsing backtick spans' do
|
68
|
+
before do
|
69
|
+
@parser = Wikitext::Parser.new
|
70
|
+
end
|
71
|
+
|
72
|
+
it 'should recognize paired backticks' do
|
73
|
+
@parser.parse('foo `bar` baz').should == "<p>foo <tt>bar</tt> baz</p>\n"
|
74
|
+
end
|
75
|
+
|
76
|
+
it 'should automatically insert missing closing backtick' do
|
77
|
+
@parser.parse('foo `bar').should == "<p>foo <tt>bar</tt></p>\n"
|
78
|
+
end
|
79
|
+
|
80
|
+
it 'should automatically close unclosed spans upon hitting newline' do
|
81
|
+
@parser.parse("foo `bar\nbaz").should == "<p>foo <tt>bar</tt> baz</p>\n"
|
82
|
+
end
|
83
|
+
|
84
|
+
it 'should handle (illegal) interleaved spans' do
|
85
|
+
@parser.parse("foo `bar '''inner` baz'''").should == "<p>foo <tt>bar <strong>inner</strong></tt> baz<strong></strong></p>\n"
|
86
|
+
end
|
87
|
+
|
88
|
+
it 'should have no effect inside <pre> blocks' do
|
89
|
+
@parser.parse(' `foo`').should == "<pre>`foo`</pre>\n"
|
90
|
+
end
|
91
|
+
|
92
|
+
it 'should have no effect inside <nowiki> spans' do
|
93
|
+
@parser.parse('<nowiki>`foo`</nowiki>').should == "<p>`foo`</p>\n"
|
94
|
+
end
|
95
|
+
|
96
|
+
it 'should have no effect if a <tt> span is already open' do
|
97
|
+
@parser.parse('foo <tt>`bar`</tt> baz').should == "<p>foo <tt>`bar`</tt> baz</p>\n"
|
98
|
+
end
|
99
|
+
end
|
100
|
+
|
data/spec/ul_spec.rb
ADDED
@@ -0,0 +1,307 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
# Copyright 2007-2008 Wincent Colaiuta
|
3
|
+
# This program is free software: you can redistribute it and/or modify
|
4
|
+
# it under the terms of the GNU General Public License as published by
|
5
|
+
# the Free Software Foundation, either version 3 of the License, or
|
6
|
+
# (at your option) any later version.
|
7
|
+
#
|
8
|
+
# This program is distributed in the hope that it will be useful,
|
9
|
+
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
10
|
+
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
11
|
+
# GNU General Public License for more details.
|
12
|
+
#
|
13
|
+
# You should have received a copy of the GNU General Public License
|
14
|
+
# along with this program. If not, see <http://www.gnu.org/licenses/>.
|
15
|
+
|
16
|
+
require File.join(File.dirname(__FILE__), 'spec_helper.rb')
|
17
|
+
require 'wikitext'
|
18
|
+
|
19
|
+
describe Wikitext::Parser, 'parsing unordered lists' do
|
20
|
+
before do
|
21
|
+
@parser = Wikitext::Parser.new
|
22
|
+
end
|
23
|
+
|
24
|
+
it 'should recognize a single item list' do
|
25
|
+
@parser.parse('*foo').should == "<ul>\n <li>foo</li>\n</ul>\n"
|
26
|
+
end
|
27
|
+
|
28
|
+
it 'should allow and consume optional space after the last <ul> marker' do
|
29
|
+
@parser.parse('* foo').should == "<ul>\n <li>foo</li>\n</ul>\n" # exactly one space consumed
|
30
|
+
@parser.parse('* foo').should == "<ul>\n <li>foo</li>\n</ul>\n" # multiple spaces consumed
|
31
|
+
end
|
32
|
+
|
33
|
+
it 'should consider a space after an <ul> marker to indicate that it will be the last marker' do
|
34
|
+
@parser.parse('* * foo').should == "<ul>\n <li>* foo</li>\n</ul>\n"
|
35
|
+
end
|
36
|
+
|
37
|
+
it 'should only recognize <ul> markers if they or a direct ancestor start in the left column' do
|
38
|
+
@parser.parse(' * foo').should == "<pre>* foo</pre>\n"
|
39
|
+
end
|
40
|
+
|
41
|
+
it 'should recognize <ul> markers nested inside blockquote blocks' do
|
42
|
+
expected = dedent <<-END
|
43
|
+
<blockquote>
|
44
|
+
<ul>
|
45
|
+
<li>foo</li>
|
46
|
+
</ul>
|
47
|
+
</blockquote>
|
48
|
+
END
|
49
|
+
@parser.parse('> * foo').should == expected
|
50
|
+
end
|
51
|
+
|
52
|
+
it 'should display excess <ul> markers as literals' do
|
53
|
+
# this provides feedback to the user
|
54
|
+
@parser.parse('** foo').should == "<ul>\n <li>* foo</li>\n</ul>\n"
|
55
|
+
@parser.parse('*** foo').should == "<ul>\n <li>** foo</li>\n</ul>\n"
|
56
|
+
end
|
57
|
+
|
58
|
+
it 'should recognize a multi-item, single-level list' do
|
59
|
+
expected = dedent <<-END
|
60
|
+
<ul>
|
61
|
+
<li>foo</li>
|
62
|
+
<li>bar</li>
|
63
|
+
</ul>
|
64
|
+
END
|
65
|
+
@parser.parse("* foo\n* bar").should == expected
|
66
|
+
end
|
67
|
+
|
68
|
+
it 'should recognize a multi-item, nested list (two levels)' do
|
69
|
+
# indentation of nested lists is tricky
|
70
|
+
# the last </li> appears too far to the left
|
71
|
+
# the difficult is that sometimes li has to act like a block level element (like blockquote, does emit before dedent)
|
72
|
+
# and at other times it has to act like p (doesn't emit before dedent)
|
73
|
+
# so basically when nested we need to do an emitting dedent
|
74
|
+
# and when not we need to do a non-emitting one
|
75
|
+
expected = dedent <<-END
|
76
|
+
<ul>
|
77
|
+
<li>foo
|
78
|
+
<ul>
|
79
|
+
<li>bar</li>
|
80
|
+
</ul>
|
81
|
+
</li>
|
82
|
+
</ul>
|
83
|
+
END
|
84
|
+
@parser.parse("* foo\n** bar").should == expected
|
85
|
+
end
|
86
|
+
|
87
|
+
it 'should recognize a multi-item, nested list (three levels)' do
|
88
|
+
expected = dedent <<-END
|
89
|
+
<ul>
|
90
|
+
<li>foo
|
91
|
+
<ul>
|
92
|
+
<li>bar
|
93
|
+
<ul>
|
94
|
+
<li>baz</li>
|
95
|
+
</ul>
|
96
|
+
</li>
|
97
|
+
</ul>
|
98
|
+
</li>
|
99
|
+
</ul>
|
100
|
+
END
|
101
|
+
@parser.parse("* foo\n** bar\n*** baz").should == expected
|
102
|
+
end
|
103
|
+
|
104
|
+
it 'should recognize lists in which nesting level increases and then is maintained' do
|
105
|
+
expected = dedent <<-END
|
106
|
+
<ul>
|
107
|
+
<li>foo
|
108
|
+
<ul>
|
109
|
+
<li>bar</li>
|
110
|
+
<li>baz</li>
|
111
|
+
</ul>
|
112
|
+
</li>
|
113
|
+
</ul>
|
114
|
+
END
|
115
|
+
@parser.parse("* foo\n** bar\n** baz").should == expected
|
116
|
+
end
|
117
|
+
|
118
|
+
it 'should recognize lists in which nesting level increases and then decreases' do
|
119
|
+
expected = dedent <<-END
|
120
|
+
<ul>
|
121
|
+
<li>foo
|
122
|
+
<ul>
|
123
|
+
<li>bar</li>
|
124
|
+
</ul>
|
125
|
+
</li>
|
126
|
+
<li>baz</li>
|
127
|
+
</ul>
|
128
|
+
END
|
129
|
+
@parser.parse("* foo\n** bar\n* baz").should == expected
|
130
|
+
end
|
131
|
+
|
132
|
+
it 'should be terminated by subsequent paragraph at the same level' do
|
133
|
+
expected = dedent <<-END
|
134
|
+
<ul>
|
135
|
+
<li>foo</li>
|
136
|
+
</ul>
|
137
|
+
<p>bar</p>
|
138
|
+
END
|
139
|
+
@parser.parse("* foo\nbar").should == expected
|
140
|
+
end
|
141
|
+
|
142
|
+
it 'should be terminated by subsequent blockquote at the same level' do
|
143
|
+
expected = dedent <<-END
|
144
|
+
<ul>
|
145
|
+
<li>foo</li>
|
146
|
+
</ul>
|
147
|
+
<blockquote>
|
148
|
+
<p>bar</p>
|
149
|
+
</blockquote>
|
150
|
+
END
|
151
|
+
@parser.parse("* foo\n> bar").should == expected
|
152
|
+
end
|
153
|
+
|
154
|
+
it 'should be terminated by subsequent heading at the same level' do
|
155
|
+
@parser.parse("* foo\n====== bar ======").should == "<ul>\n <li>foo</li>\n</ul>\n<h6>bar</h6>\n"
|
156
|
+
@parser.parse("* foo\n===== bar =====").should == "<ul>\n <li>foo</li>\n</ul>\n<h5>bar</h5>\n"
|
157
|
+
@parser.parse("* foo\n==== bar ====").should == "<ul>\n <li>foo</li>\n</ul>\n<h4>bar</h4>\n"
|
158
|
+
@parser.parse("* foo\n=== bar ===").should == "<ul>\n <li>foo</li>\n</ul>\n<h3>bar</h3>\n"
|
159
|
+
@parser.parse("* foo\n== bar ==").should == "<ul>\n <li>foo</li>\n</ul>\n<h2>bar</h2>\n"
|
160
|
+
@parser.parse("* foo\n= bar =").should == "<ul>\n <li>foo</li>\n</ul>\n<h1>bar</h1>\n"
|
161
|
+
end
|
162
|
+
|
163
|
+
it 'should be terminated by subsequent <pre> block at the same level' do
|
164
|
+
@parser.parse("* foo\n bar").should == "<ul>\n <li>foo</li>\n</ul>\n<pre>bar</pre>\n"
|
165
|
+
end
|
166
|
+
|
167
|
+
it 'should be terminated by subsequent ordered list at the same level' do
|
168
|
+
expected = dedent 6,<<-END
|
169
|
+
<ul>
|
170
|
+
<li>foo</li>
|
171
|
+
</ul>
|
172
|
+
<ol>
|
173
|
+
<li>bar</li>
|
174
|
+
</ol>
|
175
|
+
END
|
176
|
+
@parser.parse("* foo\n# bar").should == expected
|
177
|
+
end
|
178
|
+
|
179
|
+
it 'should recognize lists which contain nested ordered lists' do
|
180
|
+
expected = dedent <<-END
|
181
|
+
<ul>
|
182
|
+
<li>foo
|
183
|
+
<ol>
|
184
|
+
<li>bar</li>
|
185
|
+
</ol>
|
186
|
+
</li>
|
187
|
+
</ul>
|
188
|
+
END
|
189
|
+
@parser.parse("* foo\n*# bar").should == expected
|
190
|
+
|
191
|
+
input = dedent <<-END
|
192
|
+
* foo
|
193
|
+
*# bar
|
194
|
+
*# baz
|
195
|
+
END
|
196
|
+
expected = dedent <<-END
|
197
|
+
<ul>
|
198
|
+
<li>foo
|
199
|
+
<ol>
|
200
|
+
<li>bar</li>
|
201
|
+
<li>baz</li>
|
202
|
+
</ol>
|
203
|
+
</li>
|
204
|
+
</ul>
|
205
|
+
END
|
206
|
+
@parser.parse(input).should == expected
|
207
|
+
end
|
208
|
+
|
209
|
+
it 'should automatically close open TT_START elements on reaching the end of the line' do
|
210
|
+
# this (and the same for all other span-level elements) was a bug
|
211
|
+
input = dedent <<-END
|
212
|
+
* <tt>hello
|
213
|
+
* world
|
214
|
+
END
|
215
|
+
expected = dedent <<-END
|
216
|
+
<ul>
|
217
|
+
<li><tt>hello</tt></li>
|
218
|
+
<li>world</li>
|
219
|
+
</ul>
|
220
|
+
END
|
221
|
+
@parser.parse(input).should == expected
|
222
|
+
end
|
223
|
+
|
224
|
+
it 'should automatically close open TT elements on reaching the end of the line' do
|
225
|
+
input = dedent <<-END
|
226
|
+
* `hello
|
227
|
+
* world
|
228
|
+
END
|
229
|
+
expected = dedent <<-END
|
230
|
+
<ul>
|
231
|
+
<li><tt>hello</tt></li>
|
232
|
+
<li>world</li>
|
233
|
+
</ul>
|
234
|
+
END
|
235
|
+
@parser.parse(input).should == expected
|
236
|
+
end
|
237
|
+
|
238
|
+
it 'should automatically close open EM_START elements on reaching the end of the line' do
|
239
|
+
input = dedent <<-END
|
240
|
+
* <em>hello
|
241
|
+
* world
|
242
|
+
END
|
243
|
+
expected = dedent <<-END
|
244
|
+
<ul>
|
245
|
+
<li><em>hello</em></li>
|
246
|
+
<li>world</li>
|
247
|
+
</ul>
|
248
|
+
END
|
249
|
+
@parser.parse(input).should == expected
|
250
|
+
end
|
251
|
+
|
252
|
+
it 'should automatically close open EM elements on reaching the end of the line' do
|
253
|
+
input = dedent <<-END
|
254
|
+
* ''hello
|
255
|
+
* world
|
256
|
+
END
|
257
|
+
expected = dedent <<-END
|
258
|
+
<ul>
|
259
|
+
<li><em>hello</em></li>
|
260
|
+
<li>world</li>
|
261
|
+
</ul>
|
262
|
+
END
|
263
|
+
@parser.parse(input).should == expected
|
264
|
+
end
|
265
|
+
|
266
|
+
it 'should automatically close open STRONG_START elements on reaching the end of the line' do
|
267
|
+
input = dedent <<-END
|
268
|
+
* <strong>hello
|
269
|
+
* world
|
270
|
+
END
|
271
|
+
expected = dedent <<-END
|
272
|
+
<ul>
|
273
|
+
<li><strong>hello</strong></li>
|
274
|
+
<li>world</li>
|
275
|
+
</ul>
|
276
|
+
END
|
277
|
+
@parser.parse(input).should == expected
|
278
|
+
end
|
279
|
+
|
280
|
+
it 'should automatically close open STRONG elements on reaching the end of the line' do
|
281
|
+
input = dedent <<-END
|
282
|
+
* '''hello
|
283
|
+
* world
|
284
|
+
END
|
285
|
+
expected = dedent <<-END
|
286
|
+
<ul>
|
287
|
+
<li><strong>hello</strong></li>
|
288
|
+
<li>world</li>
|
289
|
+
</ul>
|
290
|
+
END
|
291
|
+
@parser.parse(input).should == expected
|
292
|
+
end
|
293
|
+
|
294
|
+
it 'should automatically close open STRONG_EM elements on reaching the end of the line' do
|
295
|
+
input = dedent <<-END
|
296
|
+
* '''''hello
|
297
|
+
* world
|
298
|
+
END
|
299
|
+
expected = dedent <<-END
|
300
|
+
<ul>
|
301
|
+
<li><strong><em>hello</em></strong></li>
|
302
|
+
<li>world</li>
|
303
|
+
</ul>
|
304
|
+
END
|
305
|
+
@parser.parse(input).should == expected
|
306
|
+
end
|
307
|
+
end
|
@@ -0,0 +1,50 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
# Copyright 2007-2008 Wincent Colaiuta
|
3
|
+
# This program is free software: you can redistribute it and/or modify
|
4
|
+
# it under the terms of the GNU General Public License as published by
|
5
|
+
# the Free Software Foundation, either version 3 of the License, or
|
6
|
+
# (at your option) any later version.
|
7
|
+
#
|
8
|
+
# This program is distributed in the hope that it will be useful,
|
9
|
+
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
10
|
+
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
11
|
+
# GNU General Public License for more details.
|
12
|
+
#
|
13
|
+
# You should have received a copy of the GNU General Public License
|
14
|
+
# along with this program. If not, see <http://www.gnu.org/licenses/>.
|
15
|
+
|
16
|
+
require File.join(File.dirname(__FILE__), 'spec_helper.rb')
|
17
|
+
require 'wikitext'
|
18
|
+
|
19
|
+
describe Wikitext::Parser, 'parsing non-ASCII input' do
|
20
|
+
before do
|
21
|
+
@parser = Wikitext::Parser.new
|
22
|
+
end
|
23
|
+
|
24
|
+
it 'should convert non-ASCII characters to numeric entities' do
|
25
|
+
@parser.parse('€').should == "<p>€</p>\n"
|
26
|
+
end
|
27
|
+
end
|
28
|
+
|
29
|
+
describe Wikitext::Parser, 'parsing characters which have special meaning in HTML' do
|
30
|
+
before do
|
31
|
+
@parser = Wikitext::Parser.new
|
32
|
+
end
|
33
|
+
|
34
|
+
it 'should convert "<" into the corresponding named entity' do
|
35
|
+
@parser.parse('<').should == "<p><</p>\n"
|
36
|
+
end
|
37
|
+
|
38
|
+
it 'should convert ">" into the corresponding named entity' do
|
39
|
+
# can't put ">" in the first column as that would indicate a blockquote
|
40
|
+
@parser.parse("foo >").should == "<p>foo ></p>\n"
|
41
|
+
end
|
42
|
+
|
43
|
+
it 'should convert "&" into the corresponding named entity' do
|
44
|
+
@parser.parse('&').should == "<p>&</p>\n"
|
45
|
+
end
|
46
|
+
|
47
|
+
it 'should convert \'"\' into the corresponding named entity' do
|
48
|
+
@parser.parse('"').should == "<p>"</p>\n"
|
49
|
+
end
|
50
|
+
end
|