* lib/rdoc/cross_reference.rb: Fixed matching of C#=== or #===. RDoc

  bug #164
* test/rdoc/test_rdoc_cross_reference.rb:  Test for above.

* lib/rdoc/parser/changelog.rb:  Fixed parsing of dates.  RDoc bug #165
* test/rdoc/test_rdoc_parser_changelog.rb:  Test for above.

* lib/rdoc/parser.rb:  Fixed parsing multibyte files with incomplete
  characters at byte 1024.  [ruby-trunk - Bug #6393]
  Fixed handling of -E.  [ruby-trunk - Bug #6392]
* test/rdoc/test_rdoc_options.rb:  Test for above.
* test/rdoc/test_rdoc_parser.rb:  ditto.
* test/rdoc/test_rdoc_parser_c.rb:  ditto.
* test/rdoc/test_rdoc_parser_changelog.rb:  ditto.
* test/rdoc/test_rdoc_parser_markdown.rb:  ditto.
* test/rdoc/test_rdoc_parser_rd.rb:  ditto.
* test/rdoc/test_rdoc_rdoc.rb:  ditto.

* lib/rdoc/tom_doc.rb:  Fixed parsing of [] in TomDoc arguments list.
  RDoc bug #167
* test/rdoc/test_rdoc_tom_doc.rb:  Test for above.

* lib/rdoc.rb:  Update version.


git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@38690 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

4 files changed, 37 insertions, 12 deletions

diff --git a/lib/rdoc/cross_reference.rb b/lib/rdoc/cross_reference.rb
index c6f127387c..2cb0571732 100644
--- a/lib/rdoc/cross_reference.rb
+++ b/lib/rdoc/cross_reference.rb
@@ -18,7 +18,7 @@ class RDoc::CrossReference
   #
   # See CLASS_REGEXP_STR
 
-  METHOD_REGEXP_STR = '([a-z]\w*[!?=]?|%)(?:\([\w.+*/=<>-]*\))?'
+  METHOD_REGEXP_STR = '([a-z]\w*[!?=]?|%|===)(?:\([\w.+*/=<>-]*\))?'
 
   ##
   # Regular expressions matching text that should potentially have
diff --git a/lib/rdoc/parser.rb b/lib/rdoc/parser.rb
index 506b5e7d1b..47ecd746d0 100644
--- a/lib/rdoc/parser.rb
+++ b/lib/rdoc/parser.rb
@@ -58,7 +58,7 @@ class RDoc::Parser
     old_ext = old_ext.sub(/^\.(.*)/, '\1')
     new_ext = new_ext.sub(/^\.(.*)/, '\1')
 
-    parser = can_parse "xxx.#{old_ext}"
+    parser = can_parse_by_name "xxx.#{old_ext}"
     return false unless parser
 
     RDoc::Parser.parsers.unshift [/\.#{new_ext}$/, parser]
@@ -77,14 +77,14 @@ class RDoc::Parser
 
     have_encoding = s.respond_to? :encoding
 
-    if have_encoding then
-      return false if s.encoding != Encoding::ASCII_8BIT and s.valid_encoding?
-    end
-
     return true if s[0, 2] == Marshal.dump('')[0, 2] or s.index("\x00")
 
     if have_encoding then
-      s.force_encoding Encoding.default_external
+      mode = "r"
+      s.sub!(/\A#!.*\n/, '')     # assume shebang line isn't longer than 1024.
+      encoding = s[/^\s*\#\s*(?:-\*-\s*)?(?:en)?coding:\s*([^\s;]+?)(?:-\*-|[\s;])/, 1]
+      mode = "r:#{encoding}" if encoding
+      s = File.open(file, mode) {|f| f.gets(nil, 1024)}
 
       not s.valid_encoding?
     else
@@ -131,23 +131,36 @@ class RDoc::Parser
     zip_signature == "PK\x03\x04" or
       zip_signature == "PK\x05\x06" or
       zip_signature == "PK\x07\x08"
+  rescue
+    false
   end
 
   ##
   # Return a parser that can handle a particular extension
 
-  def self.can_parse(file_name)
-    parser = RDoc::Parser.parsers.find { |regexp,| regexp =~ file_name }.last
+  def self.can_parse file_name
+    parser = can_parse_by_name file_name
 
     # HACK Selenium hides a jar file using a .txt extension
     return if parser == RDoc::Parser::Simple and zip? file_name
 
+    parser
+  end
+
+  ##
+  # Returns a parser that can handle the extension for +file_name+.  This does
+  # not depend upon the file being readable.
+
+  def self.can_parse_by_name file_name
+    _, parser = RDoc::Parser.parsers.find { |regexp,| regexp =~ file_name }
+
     # The default parser must not parse binary files
     ext_name = File.extname file_name
     return parser if ext_name.empty?
+
     if parser == RDoc::Parser::Simple and ext_name !~ /txt|rdoc/ then
       case check_modeline file_name
-      when 'rdoc' then # continue
+      when nil, 'rdoc' then # continue
       else return nil
       end
     end
@@ -173,6 +186,8 @@ class RDoc::Parser
       type = $1
     end
 
+    return nil if /coding:/i =~ type
+
     type.downcase
   rescue ArgumentError # invalid byte sequence, etc.
   end
@@ -204,6 +219,8 @@ class RDoc::Parser
     return unless parser
 
     parser.new top_level, file_name, content, options, stats
+  rescue SystemCallError
+    nil
   end
 
   ##
diff --git a/lib/rdoc/parser/changelog.rb b/lib/rdoc/parser/changelog.rb
index fd7114daee..782d8f09bf 100644
--- a/lib/rdoc/parser/changelog.rb
+++ b/lib/rdoc/parser/changelog.rb
@@ -102,7 +102,12 @@ class RDoc::Parser::ChangeLog < RDoc::Parser
 
   def group_entries entries
     entries.group_by do |title, _|
-      Time.parse(title).strftime "%Y-%m-%d"
+      begin
+        Time.parse(title).strftime '%Y-%m-%d'
+      rescue NoMethodError, ArgumentError
+        time, = title.split '  ', 2
+        Time.parse(time).strftime '%Y-%m-%d'
+      end
     end
   end
 
@@ -139,6 +144,9 @@ class RDoc::Parser::ChangeLog < RDoc::Parser
           time = Time.parse entry_name
           # HACK Ruby 1.8 does not raise ArgumentError for Time.parse "Other"
           entry_name = nil unless entry_name =~ /#{time.year}/
+        rescue NoMethodError
+          time, = entry_name.split '  ', 2
+          time = Time.parse time
         rescue ArgumentError
           entry_name = nil
         end
diff --git a/lib/rdoc/tom_doc.rb b/lib/rdoc/tom_doc.rb
index b95ef25d99..3a5a098ae8 100644
--- a/lib/rdoc/tom_doc.rb
+++ b/lib/rdoc/tom_doc.rb
@@ -218,7 +218,7 @@ class RDoc::TomDoc < RDoc::Markup::Parser
                    @tokens << [:HEADER, 3, *token_pos(pos)]
 
                    [:TEXT, @s[1], *token_pos(pos)]
-                 when @s.scan(/([:\w]\w*)[ ]+- /) then
+                 when @s.scan(/([:\w][\w\[\]]*)[ ]+- /) then
                    [:NOTE, @s[1], *token_pos(pos)]
                  else
                    @s.scan(/.*/)