Block comment parsing: basics.

Block comments are parsed out, but the commentchar removal isn't working
yet.  I'll refactor that code out of it's current home, and move it into
`parse`, as I need to know what _kind_ of comment it is that I'm
stripping.  Carrying that metadata around doesn't make any sense, so
I'll just convert the comment on the fly into a set of non-comment
strings.

lib/rocco.rb

@@ -112,7 +112,7 @@ class Rocco
     # into the comment_char syntax (we'll discuss that syntax in detail when
     # we get to `generate_comment_chars()` in a moment.
     else
-      @options[:comment_chars]    = { :single => @options[:comment_chars], :multi => "" }
+      @options[:comment_chars]    = { :single => @options[:comment_chars], :multi => nil }
     end
 
     # Turn `:comment_chars` into a regex matching a series of spaces, the 
@@ -241,9 +241,42 @@ class Rocco
     lines = data.split("\n")
     lines.shift if lines[0] =~ /^\#\!/
     lines.shift if lines[0] =~ /coding[:=]\s*[-\w.]+/ and [ "python", "rb" ].include? @options[:language]
+
+    # To detect both block comments and single-line comments, we'll set
+    # up a tiny state machine, and loop through each line of the file.
+    # This requires an `in_comment_block` boolean, and a few regular 
+    # expressions for line tests.
+    in_comment_block    = false
+    single_line_comment, block_comment_start, block_comment_end = nil, nil, nil
+    if not @options[:comment_chars][:single].nil?
+      single_line_comment = Regexp.new("^\\s*#{Regexp.escape(@options[:comment_chars][:single])}\s?")
+    end
+    if not @options[:comment_chars][:multi].nil?
+      require 'pp'
+      pp @options[:comment_chars]
+      block_comment_start = Regexp.new("^\\s*#{Regexp.escape(@options[:comment_chars][:multi][:start])}\s*$")
+      block_comment_end   = Regexp.new("^\\s*#{Regexp.escape(@options[:comment_chars][:multi][:end])}\s*$")
+    end
     lines.each do |line|
-      case line
-      when @comment_pattern
+      # If we're currently in a comment block, check whether the line matches
+      # the _end_ of a comment block.
+      if in_comment_block
+        if block_comment_end && line.match( block_comment_end )
+          in_comment_block = false
+        else
+          docs << line
+        end
+      # Otherwise, check whether the line matches the beginning of a block, or
+      # a single-line comment all on it's lonesome.  In either case, if there's
+      # code, start a new section
+      else
+        if block_comment_start && line.match( block_comment_start )
+          in_comment_block = true
+          if code.any?
+            sections << [docs, code]
+            docs, code = [], []
+          end
+        elsif single_line_comment && line.match( single_line_comment )
           if code.any?
             sections << [docs, code]
             docs, code = [], []
@@ -253,6 +286,7 @@ class Rocco
           code << line
         end
       end
+    end
     sections << [docs, code] if docs.any? || code.any?
     sections
   end

test/test_block_comments.rb

@@ -0,0 +1,36 @@
+require File.dirname(__FILE__) + '/helper'
+
+class RoccoBlockCommentTest < Test::Unit::TestCase
+    def test_basics
+        r = Rocco.new( 'test', '', { :language => "c" } ) { "" } # Generate throwaway instance so I can test `parse`
+        assert_equal(
+            [
+                [ [ " * Comment 1" ], [ "def codeblock", "end" ] ]
+            ],
+            r.parse( "/**\n * Comment 1\n*/\ndef codeblock\nend\n" )
+        )
+        assert_equal(
+            [
+                [ [ " * Comment 1a", " * Comment 1b" ], [ "def codeblock", "end" ] ]
+            ],
+            r.parse( "/**\n * Comment 1a\n * Comment 1b\n*/\ndef codeblock\nend\n" )
+        )
+    end
+    def test_multiple_blocks
+        r = Rocco.new( 'test', '', { :language => "c" } ) { "" } # Generate throwaway instance so I can test `parse`
+        assert_equal(
+            [
+                [ [ " * Comment 1" ], [ "def codeblock", "end" ] ],
+                [ [ " * Comment 2" ], [] ]
+            ],
+            r.parse( "/**\n * Comment 1\n*/\ndef codeblock\nend\n/**\n * Comment 2\n*/\n" )
+        )
+        assert_equal(
+            [
+                [ [ " * Comment 1" ], [ "def codeblock", "end" ] ],
+                [ [ " * Comment 2" ], [ "if false", "end" ] ]
+            ],
+            r.parse( "/**\n * Comment 1\n*/\ndef codeblock\nend\n/**\n * Comment 2\n*/\nif false\nend" )
+        )
+    end
+end