05_markdown.tests.rb

来自「用ruby on rails写的一个博客程序,还不错..ruby on rail」· RB 代码 · 共 1,528 行 · 第 1/3 页

#!/usr/bin/ruby
#
# Test case for BlueCloth Markdown transforms.
# $Id: TEMPLATE.rb.tpl,v 1.2 2003/09/11 04:59:51 deveiant Exp $
#
# Copyright (c) 2004 The FaerieMUD Consortium.
# 

if !defined?( BlueCloth ) || !defined?( BlueCloth::TestCase )
	basedir = File::dirname( __FILE__ )
	require File::join( basedir, 'bctestcase' )
end


### This test case tests ...
class SubfunctionsTestCase < BlueCloth::TestCase

	### Test email address output
	Emails = %w[
		[e-mail]
		[e-mail]
		[e-mail]
		[e-mail]
		[e-mail]
		[e-mail]
		[e-mail]
		[e-mail]
		[e-mail]
		[e-mail]
		[e-mail]
		[e-mail]
		[e-mail]
	]
	# I can't see a way to handle IDNs clearly yet, so these will have to wait.
	#	info@鰇o.de
	#	jemand@b黵o.de
	#	irgendwo-interre遖nt@d舋ta.se
	#]

	def test_10_email_address
		printTestHeader "BlueCloth: Inline email address"
		rval = match = nil

		Emails.each {|addr|
			assert_nothing_raised {
				rval = BlueCloth::new( "<#{addr}>" ).to_html
			}

			match = %r{<p><a href="([^\"]+)">[^<]+</a></p>}.match( rval )
			assert_not_nil match, "Match against output #{rval}"
			assert_equal "mailto:#{addr}", decode( match[1] )
		}
	end


	def decode( str )
		str.gsub( /&#(x[a-f0-9]+|\d{3});/i ) {|match|
			code = $1
			debugMsg "Decoding %p" % code

			case code
			when /^x([a-f0-9]+)/i
				debugMsg "  (hex) = %p" % $1.to_i(16).chr
				$1.to_i(16).chr
			when /\d{3}/
				debugMsg "  (oct) = %p" % code.to_i.chr
				code.to_i.chr
			else
				raise "Hmmm... malformed entity %p" % code
			end
		} 
	end



	#################################################################
	###	A U T O - G E N E R A T E D   T E S T S
	#################################################################

	# Parse the data section into a hash of test specifications
	TestSets = {}
	begin
		seenEnd = false
		inMetaSection = true
		inInputSection = true
		section, description, input, output = '', '', '', ''
		linenum = 0

		# Read this file, skipping lines until the __END__ token. Then start
		# reading the tests.
		File::foreach( __FILE__ ) {|line|
			linenum += 1
			if /^__END__/ =~ line then seenEnd = true; next end
			debugMsg "#{linenum}: #{line.chomp}"
			next unless seenEnd

			# Start off in the meta section, which has sections and
			# descriptions.
			if inMetaSection
				
				case line

				# Left angles switch into data section for the current section
				# and description.
				when /^<<</
					inMetaSection = false
					next

				# Section headings look like:
				# ### [Code blocks]
				when /^### \[([^\]]+)\]/
					section = $1.chomp
					TestSets[ section ] ||= {}

				# Descriptions look like:
				# # Para plus code block
				when /^# (.*)/
					description = $1.chomp
					TestSets[ section ][ description ] ||= {
						:line => linenum,
						:sets => [],
					}

				end

			# Data section has input and expected output parts
			else

				case line

				# Right angles terminate a data section, at which point we
				# should have enough data to add a test.
				when /^>>>/
					TestSets[ section ][ description ][:sets] << [ input.chomp, output.chomp ]

					inMetaSection = true
					inInputSection = true
					input = ''; output = ''

				# 3-Dashed divider with text divides input from output
				when /^--- (.+)/
					inInputSection = false

				# Anything else adds to either input or output
				else
					if inInputSection
						input += line
					else
						output += line
					end
				end
			end
		}			
	end

	debugMsg "Test sets: %p" % TestSets

	# Auto-generate tests out of the test specifications
	TestSets.each {|sname, section|

		# Generate a test method for each section
		section.each do |desc, test|
			methname = "test_%03d_%s" %
				[ test[:line], desc.gsub(/\W+/, '_').downcase ]

			# Header
			code = %{
				def #{methname}
					printTestHeader "BlueCloth: #{desc}"
					rval = nil
			}

			# An assertion for each input/output pair
			test[:sets].each {|input, output|
				code << %{
					assert_nothing_raised {
						obj = BlueCloth::new(%p)
						rval = obj.to_html
					}
					assert_equal %p, rval

				} % [ input, output ]
			}

			code << %{
				end
			}


			debugMsg "--- %s [%s]:\n%s\n---\n" % [sname, desc, code]
			eval code
		end

	}

end


__END__

### [Paragraphs and Line Breaks]

# Paragraphs
<<<
This is some stuff that should all be 
put in one paragraph
even though 
it occurs over several lines.

And this is a another
one.
--- Should become:
<p>This is some stuff that should all be 
put in one paragraph
even though 
it occurs over several lines.</p>

<p>And this is a another
one.</p>
>>>

# Line breaks
<<<
Mostly the same kind of thing  
with two spaces at the end  
of each line  
should result in  
line breaks, though.

And this is a another  
one.
--- Should become:
<p>Mostly the same kind of thing<br/>
with two spaces at the end<br/>
of each line<br/>
should result in<br/>
line breaks, though.</p>

<p>And this is a another<br/>
one.</p>
>>>

# Escaping special characters
<<<
The left shift operator, which is written as <<, is often used & greatly admired.
--- Should become:
<p>The left shift operator, which is written as &lt;&lt;, is often used &amp; greatly admired.</p>
>>>

# Preservation of named entities
<<<
The left shift operator, which is written as &lt;&lt;, is often used &amp; greatly admired.
--- Should become:
<p>The left shift operator, which is written as &lt;&lt;, is often used &amp; greatly admired.</p>
>>>

# Preservation of decimal-encoded entities
<<<
The left shift operator, which is written as &#060;&#060;, is often used &#038; greatly admired.
--- Should become:
<p>The left shift operator, which is written as &#060;&#060;, is often used &#038; greatly admired.</p>
>>>

# Preservation of hex-encoded entities
<<<
The left shift operator, which is written as &#x3c;&#x3c;, is often used &#x26; greatly admired.
--- Should become:
<p>The left shift operator, which is written as &#x3c;&#x3c;, is often used &#x26; greatly admired.</p>
>>>

# Inline HTML - table tags
<<<
This is a regular paragraph.

<table>
    <tr>
        <td>Foo</td>
    </tr>
</table>

This is another regular paragraph.
--- Should become:
<p>This is a regular paragraph.</p>

<table>
    <tr>
        <td>Foo</td>
    </tr>
</table>

<p>This is another regular paragraph.</p>
>>>

# Inline HTML - div tags
<<<
This is a regular paragraph.

<div>
   Something
</div>
Something else.
--- Should become:
<p>This is a regular paragraph.</p>

<div>
   Something
</div>

<p>Something else.</p>
>>>


# Inline HTML - Plain HR
<<<
This is a regular paragraph.

<hr />

Something else.
--- Should become:
<p>This is a regular paragraph.</p>

<hr />

<p>Something else.</p>
>>>


# Inline HTML - Fancy HR
<<<
This is a regular paragraph.

<hr class="publishers-mark" id="first-hrule" />

Something else.
--- Should become:
<p>This is a regular paragraph.</p>

<hr class="publishers-mark" id="first-hrule" />

<p>Something else.</p>
>>>


# Inline HTML - Iframe
<<<
This is a regular paragraph.

<iframe src="foo.html" id="foo-frame"></iframe>

Something else.
--- Should become:
<p>This is a regular paragraph.</p>

<iframe src="foo.html" id="foo-frame"></iframe>

<p>Something else.</p>
>>>


# Inline HTML - mathml
<<<
Examples
--------

Now that we have met some of the key players, it is time to see what we can
do. Here are some examples and comments which illustrate the use of the basic
layout and token elements. Consider the expression x2 + 4x + 4 = 0. A basic
MathML presentation encoding for this would be:

<math>
  <mrow>
	<msup>
	  <mi>x</mi>
	  <mn>2</mn>
	</msup>
	<mo>+</mo>
	<mn>4</mn>
	<mi>x</mi>
	<mo>+</mo>
	<mn>4</mn>
	<mo>=</mo>
	<mn>0</mn>
  </mrow>
</math>

This encoding will display as you would expect. However, if we were interested
in reusing this expression in unknown situations, we would likely want to spend
a little more effort analyzing and encoding the logical expression structure.

--- Should become:
<h2>Examples</h2>

<p>Now that we have met some of the key players, it is time to see what we can
do. Here are some examples and comments which illustrate the use of the basic
layout and token elements. Consider the expression x2 + 4x + 4 = 0. A basic
MathML presentation encoding for this would be:</p>

<math>
  <mrow>
    <msup>
      <mi>x</mi>
      <mn>2</mn>
    </msup>
    <mo>+</mo>
    <mn>4</mn>
    <mi>x</mi>
    <mo>+</mo>
    <mn>4</mn>
    <mo>=</mo>
    <mn>0</mn>
  </mrow>
</math>

<p>This encoding will display as you would expect. However, if we were interested
in reusing this expression in unknown situations, we would likely want to spend
a little more effort analyzing and encoding the logical expression structure.</p>
>>>


# Span-level HTML
<<<
This is some stuff with a <span class="foo">spanned bit of text</span> in
it. And <del>this *should* be a bit of deleted text</del> which should be
preserved, and part of it emphasized.
--- Should become:
<p>This is some stuff with a <span class="foo">spanned bit of text</span> in
it. And <del>this <em>should</em> be a bit of deleted text</del> which should be
preserved, and part of it emphasized.</p>
>>>

# Inline HTML (Case-sensitivity)
<<<
This is a regular paragraph.

<TABLE>
    <TR>
        <TD>Foo</TD>
    </TR>
</TABLE>

This is another regular paragraph.
--- Should become:
<p>This is a regular paragraph.</p>

<TABLE>
    <TR>
        <TD>Foo</TD>
    </TR>
</TABLE>

<p>This is another regular paragraph.</p>
>>>

# Span-level HTML (Case-sensitivity)
<<<
This is some stuff with a <SPAN CLASS="foo">spanned bit of text</SPAN> in
it. And <DEL>this *should* be a bit of deleted text</DEL> which should be
preserved, and part of it emphasized.
--- Should become:
<p>This is some stuff with a <SPAN CLASS="foo">spanned bit of text</SPAN> in
it. And <DEL>this <em>should</em> be a bit of deleted text</DEL> which should be
preserved, and part of it emphasized.</p>
>>>



### [Code spans]

# Single backtick
<<<
Making `code` work for you
--- Should become:
<p>Making <code>code</code> work for you</p>
>>>

# Literal backtick with doubling
<<<
Making `` `code` `` work for you
--- Should become:
<p>Making <code>`code`</code> work for you</p>
>>>

# Many repetitions
<<<
Making `````code````` work for you
--- Should become:
<p>Making <code>code</code> work for you</p>
>>>

# Two in a row
<<<
This `thing` should be `two` spans.
--- Should become:
<p>This <code>thing</code> should be <code>two</code> spans.</p>
>>>

# At the beginning of a newline
<<<
I should think that the
`tar` command would be universal.
--- Should become:
<p>I should think that the
<code>tar</code> command would be universal.</p>
>>>

# Entity escaping
<<<
The left angle-bracket (`&lt;`) can also be written as a decimal-encoded
(`&#060;`) or hex-encoded (`&#x3c;`) entity.