rdoc 4.2.1 → 6.3.1

data/lib/rdoc/markup/parser.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'strscan'
 
 ##
@@ -8,8 +9,9 @@ require 'strscan'
 # RDoc::Markup::ToHTML.
 #
 # The parser only handles the block-level constructs Paragraph, List,
-# ListItem, Heading, Verbatim, BlankLine and Rule.  Inline markup such as
-# <tt>\+blah\+</tt> is handled separately by RDoc::Markup::AttributeManager.
+# ListItem, Heading, Verbatim, BlankLine, Rule and BlockQuote.
+# Inline markup such as <tt>\+blah\+</tt> is handled separately by
+# RDoc::Markup::AttributeManager.
 #
 # To see what markup the Parser implements read RDoc.  To see how to use
 # RDoc markup to format text in your program read RDoc::Markup.
@@ -78,12 +80,6 @@ class RDoc::Markup::Parser
     @binary_input   = nil
     @current_token  = nil
     @debug          = false
-    @have_encoding  = Object.const_defined? :Encoding
-    @have_byteslice = ''.respond_to? :byteslice
-    @input          = nil
-    @input_encoding = nil
-    @line           = 0
-    @line_pos       = 0
     @s              = nil
     @tokens         = []
   end
@@ -250,7 +246,7 @@ class RDoc::Markup::Parser
 
     min_indent = nil
     generate_leading_spaces = true
-    line = ''
+    line = ''.dup
 
     until @tokens.empty? do
       type, data, column, = get
@@ -258,7 +254,7 @@ class RDoc::Markup::Parser
       if type == :NEWLINE then
         line << data
         verbatim << line
-        line = ''
+        line = ''.dup
         generate_leading_spaces = true
         next
       end
@@ -319,21 +315,6 @@ class RDoc::Markup::Parser
     verbatim
   end
 
-  ##
-  # The character offset for the input string at the given +byte_offset+
-
-  def char_pos byte_offset
-    if @have_byteslice then
-      @input.byteslice(0, byte_offset).length
-    elsif @have_encoding then
-      matched = @binary_input[0, byte_offset]
-      matched.force_encoding @input_encoding
-      matched.length
-    else
-      byte_offset
-    end
-  end
-
   ##
   # Pulls the next token from the stream.
 
@@ -390,6 +371,17 @@ class RDoc::Markup::Parser
       when :TEXT then
         unget
         parse_text parent, indent
+      when :BLOCKQUOTE then
+        type, _, column = get
+        if type == :NEWLINE
+          type, _, column = get
+        end
+        unget if type
+        bq = RDoc::Markup::BlockQuote.new
+        p :blockquote_start => [data, column] if @debug
+        parse bq, column
+        p :blockquote_end => indent if @debug
+        parent << bq
       when *LIST_TOKENS then
         unget
         parent << build_list(indent)
@@ -422,19 +414,52 @@ class RDoc::Markup::Parser
   end
 
   ##
-  # Creates the StringScanner
+  # A simple wrapper of StringScanner that is aware of the current column and lineno
 
-  def setup_scanner input
-    @line     = 0
-    @line_pos = 0
-    @input    = input.dup
+  class MyStringScanner
+    def initialize(input)
+      @line = @column = 0
+      @s = StringScanner.new input
+    end
+
+    def scan(re)
+      ret = @s.scan(re)
+      @column += ret.length if ret
+      ret
+    end
+
+    def unscan(s)
+      @s.pos -= s.bytesize
+      @column -= s.length
+    end
+
+    def pos
+      [@column, @line]
+    end
+
+    def newline!
+      @column = 0
+      @line += 1
+    end
 
-    if @have_encoding and not @have_byteslice then
-      @input_encoding = @input.encoding
-      @binary_input   = @input.force_encoding Encoding::BINARY
+    def eos?
+      @s.eos?
     end
 
-    @s = StringScanner.new input
+    def matched
+      @s.matched
+    end
+
+    def [](i)
+      @s[i]
+    end
+  end
+
+  ##
+  # Creates the StringScanner
+
+  def setup_scanner input
+    @s = MyStringScanner.new input
   end
 
   ##
@@ -469,31 +494,30 @@ class RDoc::Markup::Parser
       @tokens << case
                  # [CR]LF => :NEWLINE
                  when @s.scan(/\r?\n/) then
-                   token = [:NEWLINE, @s.matched, *token_pos(pos)]
-                   @line_pos = char_pos @s.pos
-                   @line += 1
+                   token = [:NEWLINE, @s.matched, *pos]
+                   @s.newline!
                    token
                  # === text => :HEADER then :TEXT
                  when @s.scan(/(=+)(\s*)/) then
                    level = @s[1].length
-                   header = [:HEADER, level, *token_pos(pos)]
+                   header = [:HEADER, level, *pos]
 
                    if @s[2] =~ /^\r?\n/ then
-                     @s.pos -= @s[2].length
+                     @s.unscan(@s[2])
                      header
                    else
                      pos = @s.pos
                      @s.scan(/.*/)
                      @tokens << header
-                     [:TEXT, @s.matched.sub(/\r$/, ''), *token_pos(pos)]
+                     [:TEXT, @s.matched.sub(/\r$/, ''), *pos]
                    end
                  # --- (at least 3) and nothing else on the line => :RULE
                  when @s.scan(/(-{3,}) *\r?$/) then
-                   [:RULE, @s[1].length - 2, *token_pos(pos)]
+                   [:RULE, @s[1].length - 2, *pos]
                  # * or - followed by white space and text => :BULLET
                  when @s.scan(/([*-]) +(\S)/) then
-                   @s.pos -= @s[2].bytesize # unget \S
-                   [:BULLET, @s[1], *token_pos(pos)]
+                   @s.unscan(@s[2])
+                   [:BULLET, @s[1], *pos]
                  # A. text, a. text, 12. text => :UALPHA, :LALPHA, :NUMBER
                  when @s.scan(/([a-z]|\d+)\. +(\S)/i) then
                    # FIXME if tab(s), the column will be wrong
@@ -502,7 +526,7 @@ class RDoc::Markup::Parser
                    # before (and provide a check for that at least in debug
                    # mode)
                    list_label = @s[1]
-                   @s.pos -= @s[2].bytesize # unget \S
+                   @s.unscan(@s[2])
                    list_type =
                      case list_label
                      when /[a-z]/ then :LALPHA
@@ -511,20 +535,24 @@ class RDoc::Markup::Parser
                      else
                        raise ParseError, "BUG token #{list_label}"
                      end
-                   [list_type, list_label, *token_pos(pos)]
+                   [list_type, list_label, *pos]
                  # [text] followed by spaces or end of line => :LABEL
                  when @s.scan(/\[(.*?)\]( +|\r?$)/) then
-                   [:LABEL, @s[1], *token_pos(pos)]
+                   [:LABEL, @s[1], *pos]
                  # text:: followed by spaces or end of line => :NOTE
                  when @s.scan(/(.*?)::( +|\r?$)/) then
-                   [:NOTE, @s[1], *token_pos(pos)]
+                   [:NOTE, @s[1], *pos]
+                 # >>> followed by end of line => :BLOCKQUOTE
+                 when @s.scan(/>>> *(\w+)?$/) then
+                   [:BLOCKQUOTE, @s[1], *pos]
                  # anything else: :TEXT
-                 else @s.scan(/(.*?)(  )?\r?$/)
-                   token = [:TEXT, @s[1], *token_pos(pos)]
+                 else
+                   @s.scan(/(.*?)(  )?\r?$/)
+                   token = [:TEXT, @s[1], *pos]
 
                    if @s[2] then
                      @tokens << token
-                     [:BREAK, @s[2], *token_pos(pos + @s[1].length)]
+                     [:BREAK, @s[2], pos[0] + @s[1].length, pos[1]]
                    else
                      token
                    end
@@ -534,16 +562,6 @@ class RDoc::Markup::Parser
     self
   end
 
-  ##
-  # Calculates the column (by character) and line of the current token based
-  # on +byte_offset+.
-
-  def token_pos byte_offset
-    offset = char_pos byte_offset
-
-    [offset - @line_pos, @line]
-  end
-
   ##
   # Returns the current token to the token stream
 
@@ -555,4 +573,3 @@ class RDoc::Markup::Parser
   end
 
 end
-

data/lib/rdoc/markup/pre_process.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 ##
 # Handle common directives that can occur in a block of text:
 #
@@ -101,12 +102,10 @@ class RDoc::Markup::PreProcess
       text = text.text
     end
 
-    encoding = text.encoding if defined?(Encoding)
-
     # regexp helper (square brackets for optional)
     # $1      $2  $3        $4      $5
     # [prefix][\]:directive:[spaces][param]newline
-    text.gsub!(/^([ \t]*(?:#|\/?\*)?[ \t]*)(\\?):(\w+):([ \t]*)(.+)?(\r?\n|$)/) do
+    text = text.gsub(/^([ \t]*(?:#|\/?\*)?[ \t]*)(\\?):(\w+):([ \t]*)(.+)?(\r?\n|$)/) do
       # skip something like ':toto::'
       next $& if $4.empty? and $5 and $5[0, 1] == ':'
 
@@ -121,10 +120,14 @@ class RDoc::Markup::PreProcess
         next "#{$1.strip}\n"
       end
 
-      handle_directive $1, $3, $5, code_object, encoding, &block
+      handle_directive $1, $3, $5, code_object, text.encoding, &block
     end
 
-    comment = text unless comment
+    if comment then
+      comment.text = text
+    else
+      comment = text
+    end
 
     self.class.post_processors.each do |handler|
       handler.call comment, code_object
@@ -151,7 +154,7 @@ class RDoc::Markup::PreProcess
 
     case directive
     when 'arg', 'args' then
-      return "#{prefix}:#{directive}: #{param}\n" unless code_object
+      return "#{prefix}:#{directive}: #{param}\n" unless code_object && code_object.kind_of?(RDoc::AnyMethod)
 
       code_object.params = param
 
@@ -175,7 +178,7 @@ class RDoc::Markup::PreProcess
 
       blankline
     when 'include' then
-      filename = param.split.first
+      filename = param.split(' ', 2).first
       include_file filename, prefix, encoding
     when 'main' then
       @options.main_page = param if @options.respond_to? :main_page
@@ -213,7 +216,7 @@ class RDoc::Markup::PreProcess
     when 'yield', 'yields' then
       return blankline unless code_object
       # remove parameter &block
-      code_object.params.sub!(/,?\s*&\w+/, '') if code_object.params
+      code_object.params = code_object.params.sub(/,?\s*&\w+/, '') if code_object.params
 
       code_object.block_params = param
 
@@ -263,6 +266,7 @@ class RDoc::Markup::PreProcess
     end
 
     content = RDoc::Encoding.read_file full_name, encoding, true
+    content = RDoc::Encoding.remove_magic_comment content
 
     # strip magic comment
     content = content.sub(/\A# .*coding[=:].*$/, '').lstrip
@@ -290,4 +294,3 @@ class RDoc::Markup::PreProcess
   end
 
 end
-

data/lib/rdoc/markup/raw.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 ##
 # A section of text that is added to the output document as-is
 

data/lib/rdoc/markup/regexp_handling.rb

@@ -0,0 +1,41 @@
+# frozen_string_literal: true
+##
+# Hold details of a regexp handling sequence
+
+class RDoc::Markup::RegexpHandling
+
+  ##
+  # Regexp handling type
+
+  attr_reader   :type
+
+  ##
+  # Regexp handling text
+
+  attr_accessor :text
+
+  ##
+  # Creates a new regexp handling sequence of +type+ with +text+
+
+  def initialize(type, text)
+    @type, @text = type, text
+  end
+
+  ##
+  # Regexp handlings are equal when the have the same text and type
+
+  def ==(o)
+    self.text == o.text && self.type == o.type
+  end
+
+  def inspect # :nodoc:
+    "#<RDoc::Markup::RegexpHandling:0x%x @type=%p, @text=%p>" % [
+      object_id, @type, text.dump]
+  end
+
+  def to_s # :nodoc:
+    "RegexpHandling: type=#{type} text=#{text.dump}"
+  end
+
+end
+

data/lib/rdoc/markup/rule.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 ##
 # A horizontal rule with a weight
 

data/lib/rdoc/markup/to_ansi.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 ##
 # Outputs RDoc markup with vibrant ANSI color!
 

data/lib/rdoc/markup/to_bs.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 ##
 # Outputs RDoc markup with hot backspace action!  You will probably need a
 # pager to use this output format.
@@ -40,7 +41,7 @@ class RDoc::Markup::ToBs < RDoc::Markup::ToRdoc
   end
 
   ##
-  # Turns on or off special handling for +convert_string+
+  # Turns on or off regexp handling for +convert_string+
 
   def annotate tag
     case tag
@@ -53,9 +54,9 @@ class RDoc::Markup::ToBs < RDoc::Markup::ToRdoc
   end
 
   ##
-  # Calls convert_string on the result of convert_special
+  # Calls convert_string on the result of convert_regexp_handling
 
-  def convert_special special
+  def convert_regexp_handling target
     convert_string super
   end
 
@@ -63,7 +64,6 @@ class RDoc::Markup::ToBs < RDoc::Markup::ToRdoc
   # Adds bold or underline mixed with backspaces
 
   def convert_string string
-    return string unless string.respond_to? :chars # your ruby is lame
     return string unless @in_b or @in_em
     chars = if @in_b then
               string.chars.map do |char| "#{char}\b#{char}" end
@@ -75,4 +75,3 @@ class RDoc::Markup::ToBs < RDoc::Markup::ToRdoc
   end
 
 end
-

data/lib/rdoc/markup/to_html.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require 'cgi'
 
 ##
@@ -51,19 +52,32 @@ class RDoc::Markup::ToHtml < RDoc::Markup::Formatter
     @th = nil
     @hard_break = "<br>\n"
 
-    # external links
-    @markup.add_special(/(?:link:|https?:|mailto:|ftp:|irc:|www\.)\S+\w/,
-                        :HYPERLINK)
-
-    add_special_RDOCLINK
-    add_special_TIDYLINK
+    init_regexp_handlings
 
     init_tags
   end
 
-  # :section: Special Handling
+  # :section: Regexp Handling
   #
-  # These methods handle special markup added by RDoc::Markup#add_special.
+  # These methods are used by regexp handling markup added by RDoc::Markup#add_regexp_handling.
+
+  ##
+  # Adds regexp handlings.
+
+  def init_regexp_handlings
+    # external links
+    @markup.add_regexp_handling(/(?:link:|https?:|mailto:|ftp:|irc:|www\.)\S+\w/,
+                                :HYPERLINK)
+    init_link_notation_regexp_handlings
+  end
+
+  ##
+  # Adds regexp handlings about link notations.
+
+  def init_link_notation_regexp_handlings
+    add_regexp_handling_RDOCLINK
+    add_regexp_handling_TIDYLINK
+  end
 
   def handle_RDOCLINK url # :nodoc:
     case url
@@ -90,14 +104,14 @@ class RDoc::Markup::ToHtml < RDoc::Markup::Formatter
   end
 
   ##
-  # +special+ is a <code><br></code>
+  # +target+ is a <code><br></code>
 
-  def handle_special_HARD_BREAK special
+  def handle_regexp_HARD_BREAK target
     '<br>'
   end
 
   ##
-  # +special+ is a potential link.  The following schemes are handled:
+  # +target+ is a potential link.  The following schemes are handled:
   #
   # <tt>mailto:</tt>::
   #   Inserted as-is.
@@ -108,14 +122,14 @@ class RDoc::Markup::ToHtml < RDoc::Markup::Formatter
   # <tt>link:</tt>::
   #   Reference to a local file relative to the output directory.
 
-  def handle_special_HYPERLINK(special)
-    url = special.text
+  def handle_regexp_HYPERLINK(target)
+    url = target.text
 
     gen_url url, url
   end
 
   ##
-  # +special+ is an rdoc-schemed link that will be converted into a hyperlink.
+  # +target+ is an rdoc-schemed link that will be converted into a hyperlink.
   #
   # For the +rdoc-ref+ scheme the named reference will be returned without
   # creating a link.
@@ -123,16 +137,16 @@ class RDoc::Markup::ToHtml < RDoc::Markup::Formatter
   # For the +rdoc-label+ scheme the footnote and label prefixes are stripped
   # when creating a link.  All other contents will be linked verbatim.
 
-  def handle_special_RDOCLINK special
-    handle_RDOCLINK special.text
+  def handle_regexp_RDOCLINK target
+    handle_RDOCLINK target.text
   end
 
   ##
-  # This +special+ is a link where the label is different from the URL
+  # This +target+ is a link where the label is different from the URL
   # <tt>label[url]</tt> or <tt>{long label}[url]</tt>
 
-  def handle_special_TIDYLINK(special)
-    text = special.text
+  def handle_regexp_TIDYLINK(target)
+    text = target.text
 
     return text unless
       text =~ /^\{(.*)\}\[(.*?)\]$/ or text =~ /^(\S+)\[(.*?)\]$/
@@ -185,7 +199,7 @@ class RDoc::Markup::ToHtml < RDoc::Markup::Formatter
     @res << "\n<p>"
     text = paragraph.text @hard_break
     text = text.gsub(/\r?\n/, ' ')
-    @res << wrap(to_html(text))
+    @res << to_html(text)
     @res << "</p>\n"
   end
 
@@ -199,11 +213,13 @@ class RDoc::Markup::ToHtml < RDoc::Markup::Formatter
 
     content = if verbatim.ruby? or parseable? text then
                 begin
-                  tokens = RDoc::RubyLex.tokenize text, @options
+                  tokens = RDoc::Parser::RipperStateLex.parse text
                   klass  = ' class="ruby"'
 
-                  RDoc::TokenStream.to_html tokens
-                rescue RDoc::RubyLex::Error
+                  result = RDoc::TokenStream.to_html tokens
+                  result = result + "\n" unless "\n" == result[-1]
+                  result
+                rescue
                   CGI.escapeHTML text
                 end
               else
@@ -211,7 +227,7 @@ class RDoc::Markup::ToHtml < RDoc::Markup::Formatter
               end
 
     if @options.pipe then
-      @res << "\n<pre><code>#{CGI.escapeHTML text}</code></pre>\n"
+      @res << "\n<pre><code>#{CGI.escapeHTML text}\n</code></pre>\n"
     else
       @res << "\n<pre#{klass}>#{content}</pre>\n"
     end
@@ -298,6 +314,29 @@ class RDoc::Markup::ToHtml < RDoc::Markup::Formatter
     @res << raw.parts.join("\n")
   end
 
+  ##
+  # Adds +table+ to the output
+
+  def accept_table header, body, aligns
+    @res << "\n<table role=\"table\">\n<thead>\n<tr>\n"
+    header.zip(aligns) do |text, align|
+      @res << '<th'
+      @res << ' align="' << align << '"' if align
+      @res << '>' << CGI.escapeHTML(text) << "</th>\n"
+    end
+    @res << "</tr>\n</thead>\n<tbody>\n"
+    body.each do |row|
+      @res << "<tr>\n"
+      row.zip(aligns) do |text, align|
+        @res << '<td'
+        @res << ' align="' << align << '"' if align
+        @res << '>' << CGI.escapeHTML(text) << "</td>\n"
+      end
+      @res << "</tr>\n"
+    end
+    @res << "</tbody>\n</table>\n"
+  end
+
   # :section: Utilities
 
   ##
@@ -309,7 +348,7 @@ class RDoc::Markup::ToHtml < RDoc::Markup::Formatter
 
   ##
   # Generate a link to +url+ with content +text+.  Handles the special cases
-  # for img: and link: described under handle_special_HYPERLINK
+  # for img: and link: described under handle_regexp_HYPERLINK
 
   def gen_url url, text
     scheme, url, id = parse_url url
@@ -318,6 +357,10 @@ class RDoc::Markup::ToHtml < RDoc::Markup::Formatter
        url =~ /\.(gif|png|jpg|jpeg|bmp)$/ then
       "<img src=\"#{url}\" />"
     else
+      if scheme != 'link' and /\.(?:rb|rdoc|md)\z/i =~ url
+        url = url.sub(%r%\A([./]*)(.*)\z%) { "#$1#{$2.tr('.', '_')}.html" }
+      end
+
       text = text.sub %r%^#{scheme}:/*%i, ''
       text = text.sub %r%^[*\^](\d+)$%,   '\1'
 
@@ -382,9 +425,12 @@ class RDoc::Markup::ToHtml < RDoc::Markup::Formatter
   # Returns true if text is valid ruby syntax
 
   def parseable? text
+    verbose, $VERBOSE = $VERBOSE, nil
     eval("BEGIN {return true}\n#{text}")
   rescue SyntaxError
     false
+  ensure
+    $VERBOSE = verbose
   end
 
   ##