bryanlarsen · January 13, 2010 13:18 · Jan 13, 2010 · Jan 13, 2010 · Jan 13, 2010 · Aug 21, 2009
diff --git a/gfm.rb b/gfm.rb
@@ -69,6 +69,10 @@ class GFMTest < Test::Unit::TestCase
         assert_equal "\n    foil\ntest foo\\_bar\\_baz and another\\_test\\_obj", gfm("\n    foil\ntest foo_bar_baz and another_test_obj")
       end
 
+      should "escape two or more underscores inside words not at front of line twice on three lines" do
+        assert_equal "\n    foil_me_twice\ntest foo\\_bar\\_baz  \n    and_again_test\n",    gfm("\n    foil_me_twice\ntest foo_bar_baz\n    and_again_test\n")
+      end
+
       should "turn newlines into br tags in simple cases" do
         assert_equal "foo  \nbar", gfm("foo\nbar")
       end

diff --git a/gfm.rb b/gfm.rb
@@ -9,9 +9,10 @@ def gfm(text)
     "{gfm-extraction-#{md5}}"
   end
 
-  # prevent foo_bar_baz from ending up with an italic word in the middle
-  text.gsub!(/(^(?! {4}|\t)\w+_\w+_\w[\w_]*)/) do |x|
-    x.gsub('_', '\_') if x.split('').sort.to_s[0..1] == '__'
+  text.gsub!(/^(?! {4}|\t).*$/) do |line|
+    line.gsub(/\w+_\w+_\w[\w_]*/) do |x|
+      x.gsub('_', '\_') if x.split('').sort.to_s[0..1] == '__'
+    end
   end
 
   # in very clear cases, let newlines become <br /> tags
@@ -60,6 +61,14 @@ class GFMTest < Test::Unit::TestCase
         assert_equal "test foo\\_bar\\_baz", gfm("test foo_bar_baz")
       end
 
+      should "escape two or more underscores inside words not at front of line twice" do
+        assert_equal "test foo\\_bar\\_baz and another\\_test\\_obj", gfm("test foo_bar_baz and another_test_obj")
+      end
+
+      should "escape two or more underscores inside words not at front of line twice on two lines" do
+        assert_equal "\n    foil\ntest foo\\_bar\\_baz and another\\_test\\_obj", gfm("\n    foil\ntest foo_bar_baz and another_test_obj")
+      end
+
       should "turn newlines into br tags in simple cases" do
         assert_equal "foo  \nbar", gfm("foo\nbar")
       end

diff --git a/gfm.rb b/gfm.rb
@@ -29,6 +29,7 @@ def gfm(text)
 
 if $0 == __FILE__
   require 'test/unit'
+  require 'rubygems'
   require 'shoulda'
 
   class GFMTest < Test::Unit::TestCase
@@ -55,6 +56,10 @@ class GFMTest < Test::Unit::TestCase
         assert_equal "foo\\_bar\\_baz", gfm("foo_bar_baz")
       end
 
+      should "escape two or more underscores inside words not at front of line" do
+        assert_equal "test foo\\_bar\\_baz", gfm("test foo_bar_baz")
+      end
+
       should "turn newlines into br tags in simple cases" do
         assert_equal "foo  \nbar", gfm("foo\nbar")
       end
@@ -75,4 +80,4 @@ class GFMTest < Test::Unit::TestCase
       end
     end
   end
-end
+end
diff --git a/gfm.rb b/gfm.rb
@@ -15,13 +15,13 @@ def gfm(text)
   end
 
   # in very clear cases, let newlines become <br /> tags
-  text.gsub!(/(\A|^$\n)(^\w[^\n]*\n)(^\w[^\n]*$)+/m) do |x|
-    x.gsub(/^(.+)$/, "\\1  ")
+  text.gsub!(/^[\w\<][^\n]*\n+/) do |x|
+    x =~ /\n{2}/ ? x : (x.strip!; x << "  \n")
   end
 
   # Insert pre block extractions
   text.gsub!(/\{gfm-extraction-([0-9a-f]{32})\}/) do
-    extractions[$1]
+    "\n\n" + extractions[$1]
   end
 
   text
@@ -42,22 +42,33 @@ class GFMTest < Test::Unit::TestCase
       end
 
       should "not touch underscores in pre blocks" do
-        assert_equal "<pre>\nfoo_bar_baz\n</pre>", gfm("<pre>\nfoo_bar_baz\n</pre>")
+        assert_equal "\n\n<pre>\nfoo_bar_baz\n</pre>", gfm("<pre>\nfoo_bar_baz\n</pre>")
+      end
+
+      should "not treat pre blocks with pre-text differently" do
+        a = "\n\n<pre>\nthis is `a\\_test` and this\\_too\n</pre>"
+        b = "hmm<pre>\nthis is `a\\_test` and this\\_too\n</pre>"
+        assert_equal gfm(a)[2..-1], gfm(b)[3..-1]
       end
 
       should "escape two or more underscores inside words" do
         assert_equal "foo\\_bar\\_baz", gfm("foo_bar_baz")
       end
 
       should "turn newlines into br tags in simple cases" do
-        assert_equal "foo  \nbar  ", gfm("foo\nbar")
+        assert_equal "foo  \nbar", gfm("foo\nbar")
       end
 
       should "convert newlines in all groups" do
         assert_equal "apple  \npear  \norange\n\nruby  \npython  \nerlang",
                      gfm("apple\npear\norange\n\nruby\npython\nerlang")
       end
 
+      should "convert newlines in even long groups" do
+        assert_equal "apple  \npear  \norange  \nbanana\n\nruby  \npython  \nerlang",
+                     gfm("apple\npear\norange\nbanana\n\nruby\npython\nerlang")
+      end
+
       should "not convert newlines in lists" do
         assert_equal "# foo\n# bar", gfm("# foo\n# bar")
         assert_equal "* foo\n* bar", gfm("* foo\n* bar")

diff --git a/gfm.rb b/gfm.rb
@@ -1,4 +1,14 @@
+require 'digest/md5'
+
 def gfm(text)
+  # Extract pre blocks
+  extractions = {}
+  text.gsub!(%r{<pre>.*?</pre>}m) do |match|
+    md5 = Digest::MD5.hexdigest(match)
+    extractions[md5] = match
+    "{gfm-extraction-#{md5}}"
+  end
+
   # prevent foo_bar_baz from ending up with an italic word in the middle
   text.gsub!(/(^(?! {4}|\t)\w+_\w+_\w[\w_]*)/) do |x|
     x.gsub('_', '\_') if x.split('').sort.to_s[0..1] == '__'
@@ -9,6 +19,11 @@ def gfm(text)
     x.gsub(/^(.+)$/, "\\1  ")
   end
 
+  # Insert pre block extractions
+  text.gsub!(/\{gfm-extraction-([0-9a-f]{32})\}/) do
+    extractions[$1]
+  end
+
   text
 end
 
@@ -22,6 +37,14 @@ class GFMTest < Test::Unit::TestCase
         assert_equal "foo_bar", gfm("foo_bar")
       end
 
+      should "not touch underscores in code blocks" do
+        assert_equal "    foo_bar_baz", gfm("    foo_bar_baz")
+      end
+
+      should "not touch underscores in pre blocks" do
+        assert_equal "<pre>\nfoo_bar_baz\n</pre>", gfm("<pre>\nfoo_bar_baz\n</pre>")
+      end
+
       should "escape two or more underscores inside words" do
         assert_equal "foo\\_bar\\_baz", gfm("foo_bar_baz")
       end

diff --git a/gfm.rb b/gfm.rb
@@ -0,0 +1,44 @@
+def gfm(text)
+  # prevent foo_bar_baz from ending up with an italic word in the middle
+  text.gsub!(/(^(?! {4}|\t)\w+_\w+_\w[\w_]*)/) do |x|
+    x.gsub('_', '\_') if x.split('').sort.to_s[0..1] == '__'
+  end
+
+  # in very clear cases, let newlines become <br /> tags
+  text.gsub!(/(\A|^$\n)(^\w[^\n]*\n)(^\w[^\n]*$)+/m) do |x|
+    x.gsub(/^(.+)$/, "\\1  ")
+  end
+
+  text
+end
+
+if $0 == __FILE__
+  require 'test/unit'
+  require 'shoulda'
+
+  class GFMTest < Test::Unit::TestCase
+    context "GFM" do
+      should "not touch single underscores inside words" do
+        assert_equal "foo_bar", gfm("foo_bar")
+      end
+
+      should "escape two or more underscores inside words" do
+        assert_equal "foo\\_bar\\_baz", gfm("foo_bar_baz")
+      end
+
+      should "turn newlines into br tags in simple cases" do
+        assert_equal "foo  \nbar  ", gfm("foo\nbar")
+      end
+
+      should "convert newlines in all groups" do
+        assert_equal "apple  \npear  \norange\n\nruby  \npython  \nerlang",
+                     gfm("apple\npear\norange\n\nruby\npython\nerlang")
+      end
+
+      should "not convert newlines in lists" do
+        assert_equal "# foo\n# bar", gfm("# foo\n# bar")
+        assert_equal "* foo\n* bar", gfm("* foo\n* bar")
+      end
+    end
+  end
+end