Module: MaRuKu::Tests

Included in:
Maruku
Defined in:
lib/maruku/tests/new_parser.rb

Constant Summary collapse

AccIta8 =

5 accented letters in italian, encoded as UTF-8

"\303\240\303\250\303\254\303\262\303\271"
AccIta1 =

Same letters, written in ISO-8859-1 (one byte per letter)

"\340\350\354\362\371"
Maruku8 =

The word MA-RU-KU, written in katakana using UTF-8

"\343\203\236\343\203\253\343\202\257"
PAD =
40

Instance Method Summary collapse

Instance Method Details

#describe_difference(input, expected, output) ⇒ Object



357
358
359
360
361
# File 'lib/maruku/tests/new_parser.rb', line 357

def describe_difference(input, expected, output)
	"\nInput:\n  #{input.inspect}" +
	    "\nExpected:\n  #{expected.inspect}" +
		"\nOutput:\n  #{output.inspect}\n"
end


346
347
348
349
350
351
352
353
354
# File 'lib/maruku/tests/new_parser.rb', line 346

def print_status(comment, status, verbose_text=nil)
	if comment.size < PAD
		comment = comment + (" "*(PAD-comment.size))
	end
	puts "- #{comment} #{status}"
	if @verbose and verbose_text
		puts verbose_text
	end
end

#test_span_parser(verbose, break_on_first_error, quiet) ⇒ Object



35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
# File 'lib/maruku/tests/new_parser.rb', line 35

def test_span_parser(verbose, break_on_first_error, quiet)
good_cases = [
	
	["",       [],         'Empty string gives empty list'],
	["a",      ["a"],      'Easy char'],
	[" a",     ["a"],      'First space in the paragraph is ignored'],
	["a\n \n", ["a"],      'Last spaces in the paragraphs are ignored'],
	[' ',      [],      'One char => nothing'],
	['  ',     [],      'Two chars => nothing'],
	['a  b',   ['a b'],    'Spaces are compressed'],
	['a  b',   ['a b'],    'Newlines are spaces'],
	["a\nb",   ['a b'],    'Newlines are spaces'],
	["a\n b",  ['a b'],    'Compress newlines 1'],
	["a \nb",  ['a b'],    'Compress newlines 2'],
	[" \nb",   ['b'],      'Compress newlines 3'],
	["\nb",    ['b'],      'Compress newlines 4'],
	["b\n",    ['b'],     'Compress newlines 5'],
	["\n",     [],      'Compress newlines 6'],
	["\n\n\n", [],      'Compress newlines 7'],
	
	[nil, :throw, "Should throw on nil input"],
	
	# Code blocks
	["`" ,   :throw,  'Unclosed single ticks'],
	["``" ,  :throw,  'Unclosed double ticks'],
	["`a`" ,     [md_code('a')],    'Simple inline code'],
	["`` ` ``" ,    [md_code('`')],   ],
	["`` \\` ``" ,    [md_code('\\`')],   ],
	["``a``" ,   [md_code('a')],    ],
	["`` a ``" ,   [md_code('a')],    ],
	
	# Newlines 
	["a  \n", ['a',md_el(:linebreak)], 'Two spaces give br.'],
	["a \n",  ['a'], 'Newlines 2'],
	["  \n",  [md_el(:linebreak)], 'Newlines 3'],
	["  \n  \n",  [md_el(:linebreak),md_el(:linebreak)],'Newlines 3'],
	["  \na  \n",  [md_el(:linebreak),'a',md_el(:linebreak)],'Newlines 3'],
	
	# Inline HTML
	["a < b", ['a < b'], '< can be on itself'],
	["<hr>",  [md_html('<hr />')], 'HR will be sanitized'],
	["<hr/>", [md_html('<hr />')], 'Closed tag is ok'],
	["<hr  />", [md_html('<hr />')], 'Closed tag is ok 2'],
	["<hr/>a", [md_html('<hr />'),'a'], 'Closed tag is ok 2'],
	["<em></em>a", [md_html('<em></em>'),'a'], 'Inline HTML 1'],
	["<em>e</em>a", [md_html('<em>e</em>'),'a'], 'Inline HTML 2'],
	["a<em>e</em>b", ['a',md_html('<em>e</em>'),'b'], 'Inline HTML 3'],
	["<em>e</em>a<em>f</em>", 
		[md_html('<em>e</em>'),'a',md_html('<em>f</em>')], 
		'Inline HTML 4'],
	["<em>e</em><em>f</em>a", 
		[md_html('<em>e</em>'),md_html('<em>f</em>'),'a'], 
		'Inline HTML 5'],
		
		["<img src='a' />", [md_html("<img src='a' />")], 'Attributes'],
		["<img src='a'/>"],
	
	# emphasis
	["**", :throw, 'Unclosed double **'],
	["\\*", ['*'], 'Escaping of *'],
	["a *b* ", ['a ', md_em('b')], 'Emphasis 1'],
	["a *b*", ['a ', md_em('b')], 'Emphasis 2'],
	["a * b", ['a * b'], 'Emphasis 3'],
	["a * b*", :throw, 'Unclosed emphasis'],
	# same with underscore
	["__", :throw, 'Unclosed double __'],
	["\\_", ['_'], 'Escaping of _'],
	["a _b_ ", ['a ', md_em('b')], 'Emphasis 4'],
	["a _b_", ['a ', md_em('b')], 'Emphasis 5'],
	["a _ b", ['a _ b'], 'Emphasis 6'],
	["a _ b_", :throw, 'Unclosed emphasis'],
	["_b_", [md_em('b')], 'Emphasis 7'],
	["_b_ _c_", [md_em('b'),' ',md_em('c')], 'Emphasis 8'],
	["_b__c_", [md_em('b'),md_em('c')], 'Emphasis 9'],
	# underscores in word
	["mod_ruby", ['mod_ruby'], 'Word with underscore'],
	# strong
	["**a*", :throw, 'Unclosed double ** 2'],
	["\\**a*", ['*', md_em('a')], 'Escaping of *'],
	["a **b** ", ['a ', md_strong('b')], 'Emphasis 1'],
	["a **b**", ['a ', md_strong('b')], 'Emphasis 2'],
	["a ** b", ['a ** b'], 'Emphasis 3'],
	["a ** b**", :throw, 'Unclosed emphasis'],
	["**b****c**", [md_strong('b'),md_strong('c')], 'Emphasis 9'],
	# strong (with underscore)
	["__a_", :throw, 'Unclosed double __ 2'],

#	["\\__a_", ['_', md_em('a')], 'Escaping of _'],
	["a __b__ ", ['a ', md_strong('b')], 'Emphasis 1'],
	["a __b__", ['a ', md_strong('b')], 'Emphasis 2'],
	["a __ b", ['a __ b'], 'Emphasis 3'],
	["a __ b__", :throw, 'Unclosed emphasis'],
	["__b____c__", [md_strong('b'),md_strong('c')], 'Emphasis 9'],
	# extra strong
	["***a**", :throw, 'Unclosed triple *** '],
	["\\***a**", ['*', md_strong('a')], 'Escaping of *'],
	["a ***b*** ", ['a ', md_emstrong('b')], 'Strong elements'],
	["a ***b***", ['a ', md_emstrong('b')]],
	["a *** b", ['a *** b']],
	["a ** * b", ['a ** * b']],
	["***b******c***", [md_emstrong('b'),md_emstrong('c')]],
	["a *** b***", :throw, 'Unclosed emphasis'],
	# same with underscores
	["___a__", :throw, 'Unclosed triple *** '],
#		["\\___a__", ['_', md_strong('a')], 'Escaping of _'],
	["a ___b___ ", ['a ', md_emstrong('b')], 'Strong elements'],
	["a ___b___", ['a ', md_emstrong('b')]],
	["a ___ b", ['a ___ b']],
	["a __ _ b", ['a __ _ b']],
	["___b______c___", [md_emstrong('b'),md_emstrong('c')]],
	["a ___ b___", :throw, 'Unclosed emphasis'],
	# mixing is bad
	["*a_", :throw, 'Mixing is bad'],
	["_a*", :throw],
	["**a__", :throw],
	["__a**", :throw],
	["___a***", :throw],
	["***a___", :throw],
	# links of the form [text][ref]
	["\\[a]",  ["[a]"], 'Escaping 1'],
	["\\[a\\]", ["[a]"], 'Escaping 2'],
# This is valid in the new Markdown version
#		["[a]",   ["a"],   'Not a link'],
	["[a]",   [ md_link(["a"],'a')], 'Empty link'],
	["[a][]", ],
	["[a][]b",   [ md_link(["a"],'a'),'b'], 'Empty link'],
	["[a\\]][]", [ md_link(["a]"],'a')], 'Escape inside link (throw ?] away)'],
	
	["[a",  :throw,   'Link not closed'],
	["[a][",  :throw,   'Ref not closed'],
	
	# links of the form [text](url)
	["\\[a](b)",  ["[a](b)"], 'Links'],
	["[a](url)c",  [md_im_link(['a'],'url'),'c'], 'url'],
	["[a]( url )c" ],
	["[a] (	url )c" ],
	["[a] (	url)c" ],
	
	["[a](ur:/l/ 'Title')",  [md_im_link(['a'],'ur:/l/','Title')],
	 	'url and title'],
	["[a] (	ur:/l/ \"Title\")" ],
	["[a] (	ur:/l/ \"Title\")" ],
	["[a]( ur:/l/ Title)", :throw, "Must quote title" ],

	["[a](url 'Tit\\\"l\\\\e')", [md_im_link(['a'],'url','Tit"l\\e')],
	 	'url and title escaped'],
	["[a] (	url \"Tit\\\"l\\\\e\")" ],
	["[a] (	url	\"Tit\\\"l\\\\e\"  )" ],
	['[a] (	url	"Tit\\"l\\\\e"  )' ],
	["[a]()", [md_im_link(['a'],'')], 'No URL is OK'],

	["[a](\"Title\")", :throw, "No url specified" ],
	["[a](url \"Title)", :throw, "Unclosed quotes" ],
	["[a](url \"Title\\\")", :throw],
	["[a](url \"Title\" ", :throw],

	["[a](url \'Title\")", :throw, "Mixing is bad" ],
	["[a](url \"Title\')"],
	
	["[a](/url)", [md_im_link(['a'],'/url')], 'Funny chars in url'],
	["[a](#url)", [md_im_link(['a'],'#url')]],
	["[a](</script?foo=1&bar=2>)", [md_im_link(['a'],'/script?foo=1&bar=2')]],
	
	
	# Images
	["\\![a](url)",  ['!', md_im_link(['a'],'url') ], 'Escaping images'],
	
	["![a](url)",  [md_im_image(['a'],'url')], 'Image no title'],
	["![a]( url )" ],
	["![a] (	url )" ],
	["![a] (	url)" ],

	["![a](url 'ti\"tle')",  [md_im_image(['a'],'url','ti"tle')], 'Image with title'],
	['![a]( url "ti\\"tle")' ],

	["![a](url", :throw, 'Invalid images'],
	["![a( url )" ],
	["![a] ('url )" ],

	["![a][imref]",  [md_image(['a'],'imref')], 'Image with ref'],
	["![a][ imref]"],
	["![a][ imref ]"],
	["![a][\timref\t]"],
	

	['<http://example.com/?foo=1&bar=2>', 
		[md_url('http://example.com/?foo=1&bar=2')], 'Immediate link'],
		['a<http://example.com/?foo=1&bar=2>b', 
			['a',md_url('http://example.com/?foo=1&bar=2'),'b']  ],
	['<[email protected]>', 
		[md_email('[email protected]')], 'Email address'],
	['<mailto:[email protected]>'],
	["Developmen <http://rubyforge.org/projects/maruku/>",
		 ["Developmen ", md_url("http://rubyforge.org/projects/maruku/")]],
	["a<!-- -->b", ['a',md_html('<!-- -->'),'b'], 
		'HTML Comment'],

	["a<!--", :throw, 'Bad HTML Comment'],
	["a<!-- ", :throw, 'Bad HTML Comment'],

	["<?xml <?!--!`3  ?>", [md_xml_instr('xml','<?!--!`3')], 'XML processing instruction'],
	["<? <?!--!`3  ?>", [md_xml_instr('','<?!--!`3')] ],

	["<? ", :throw, 'Bad Server directive'],

	["a <b", :throw, 'Bad HTML 1'],
	["<b",   :throw, 'Bad HTML 2'],
	["<b!",  :throw, 'Bad HTML 3'],
	['`<div>`, `<table>`, `<pre>`, `<p>`',
		[md_code('<div>'),', ',md_code('<table>'),', ',
			md_code('<pre>'),', ',md_code('<p>')],
			'Multiple HTLM tags'],
			
	["&andrea", ["&andrea"], 'Parsing of entities'],
# no escaping is allowed
#			["\\&andrea;", ["&andrea;"]],
	["l&andrea;", ["l", md_entity('andrea')] ],
	["&&andrea;", ["&", md_entity('andrea')] ],
	["&123;;&amp;",[md_entity('123'),';',md_entity('amp')]],
	
	["a\nThe [syntax page] [s] provides", 
		['a The ', md_link(['syntax page'],'s'), ' provides'], 'Regression'],
	
	['![a](url "ti"tle")', [md_im_image(['a'],'url','ti"tle')], 
		"Image with quotes"],
	['![a](url \'ti"tle\')' ],
	
	['[bar](/url/ "Title with "quotes" inside")', 
		[md_im_link(["bar"],'/url/', 'Title with "quotes" inside')],
		"Link with quotes"],

# We dropped this idea		
#		['$20,000 and $30,000', ['$20,000 and $30,000'], 'Math: spaces'],
	['$20,000$', [md_inline_math('20,000')]],
#		['$ 20,000$', ['$ 20,000$']],
#		['$20,000 $ $20,000$', ['$20,000 $ ', md_inline_math('20,000')]],
	["#{Maruku8}", [Maruku8], "Reading UTF-8"],
#		["#{AccIta1}", [AccIta8], "Converting ISO-8859-1 to UTF-8", 
#			{:encoding => 'iso-8859-1'}],
					
]

	good_cases = unit_tests_for_attribute_lists + good_cases
	
	count = 1; last_comment=""; last_expected=:throw
	good_cases.each do |t|
		if not t[1]
			t[1] = last_expected
		else
			last_expected = t[1]
		end				
		if not t[2]
			t[2] = last_comment + " #{count+=1}"
		else
			last_comment = t[2]; count=1
		end
	end
	
	
		
	@verbose = verbose
	m = Maruku.new
	m.attributes[:on_error] = :raise
	Globals[:debug_keep_ials] = true
	
	num_ok = 0
	good_cases.each do |input, expected, comment|
			output = nil
			begin
				output = m.parse_span_better(input)
				#lines = Maruku.split_lines input
				#output = m.parse_lines_as_span(lines)
			rescue Exception => e
				if not expected == :throw
					ex = e.inspect+ "\n"+ e.backtrace.join("\n")
					s = comment+describe_difference(input, expected, output)
						
					print_status(comment,'CRASHED :-(', ex+s)
					raise e if @break_on_first_error 
				else
					quiet || print_status(comment,'OK')
					num_ok += 1
				end
			end
			
			if not expected == :throw
				if not (expected == output)
					s = comment+describe_difference(input, expected, output)
					print_status(comment, 'FAILED', s)
					break if break_on_first_error
				else
					num_ok += 1
					quiet || print_status(comment, 'OK')
				end
			else # I expected a raise
				if output
					s = comment+describe_difference(input, expected, output)
					
					print_status(comment, 'FAILED (no throw)', s)
					break if break_on_first_error
				end
			end		
	end  # do 
	if num_ok != good_cases.size
		return false
	else
		return true
	end
end