In Files
- rdoc/encoding.rb
Methods
Class/Module Index
- RDoc
- RDoc::Alias
- RDoc::AnonClass
- RDoc::AnyMethod
- RDoc::Attr
- RDoc::ClassModule
- RDoc::CodeObject
- RDoc::Comment
- RDoc::Constant
- RDoc::Context
- RDoc::Context::Section
- RDoc::CrossReference
- RDoc::ERBIO
- RDoc::ERBPartial
- RDoc::Encoding
- RDoc::Error
- RDoc::Extend
- RDoc::Generator
- RDoc::Generator::Darkfish
- RDoc::Generator::JsonIndex
- RDoc::Generator::Markup
- RDoc::Generator::POT
- RDoc::Generator::POT::MessageExtractor
- RDoc::Generator::POT::PO
- RDoc::Generator::POT::POEntry
- RDoc::Generator::RI
- RDoc::GhostMethod
- RDoc::I18n
- RDoc::I18n::Locale
- RDoc::I18n::Text
- RDoc::Include
- RDoc::Markdown
- RDoc::Markdown::Literals
- RDoc::Markup
- RDoc::Markup::AttrChanger
- RDoc::Markup::AttrSpan
- RDoc::Markup::AttributeManager
- RDoc::Markup::Attributes
- RDoc::Markup::BlankLine
- RDoc::Markup::BlockQuote
- RDoc::Markup::Document
- RDoc::Markup::Formatter
- RDoc::Markup::FormatterTestCase
- RDoc::Markup::HardBreak
- RDoc::Markup::Include
- RDoc::Markup::IndentedParagraph
- RDoc::Markup::List
- RDoc::Markup::ListItem
- RDoc::Markup::Paragraph
- RDoc::Markup::Parser
- RDoc::Markup::Parser::Error
- RDoc::Markup::Parser::ParseError
- RDoc::Markup::PreProcess
- RDoc::Markup::Raw
- RDoc::Markup::Rule
- RDoc::Markup::Special
- RDoc::Markup::TextFormatterTestCase
- RDoc::Markup::ToAnsi
- RDoc::Markup::ToBs
- RDoc::Markup::ToHtml
- RDoc::Markup::ToHtmlCrossref
- RDoc::Markup::ToHtmlSnippet
- RDoc::Markup::ToJoinedParagraph
- RDoc::Markup::ToLabel
- RDoc::Markup::ToMarkdown
- RDoc::Markup::ToRdoc
- RDoc::Markup::ToTableOfContents
- RDoc::Markup::ToTest
- RDoc::Markup::ToTtOnly
- RDoc::Markup::Verbatim
- RDoc::MetaMethod
- RDoc::MethodAttr
- RDoc::Mixin
- RDoc::NormalClass
- RDoc::NormalModule
- RDoc::Options
- RDoc::Parser
- RDoc::Parser::C
- RDoc::Parser::ChangeLog
- RDoc::Parser::Markdown
- RDoc::Parser::RD
- RDoc::Parser::Ruby
- RDoc::Parser::RubyTools
- RDoc::Parser::Simple
- RDoc::Parser::Text
- RDoc::RD
- RDoc::RD::BlockParser
- RDoc::RD::Inline
- RDoc::RD::InlineParser
- RDoc::RDoc
- RDoc::RI
- RDoc::RI::Driver
- RDoc::RI::Driver::Error
- RDoc::RI::Driver::NotFoundError
- RDoc::RI::Error
- RDoc::RI::Paths
- RDoc::RI::Task
- RDoc::Require
- RDoc::RubyLex
- RDoc::RubyLex::Error
- RDoc::RubyToken
- RDoc::RubygemsHook
- RDoc::Servlet
- RDoc::SingleClass
- RDoc::Stats
- RDoc::Stats::Normal
- RDoc::Stats::Quiet
- RDoc::Stats::Verbose
- RDoc::Store
- RDoc::Store::Error
- RDoc::Store::MissingFileError
- RDoc::Task
- RDoc::TestCase
- RDoc::Text
- RDoc::TokenStream
- RDoc::TomDoc
- RDoc::TopLevel
- RDocTask
- Test
RDoc::Encoding
This class is a wrapper around File IO and Encoding that helps RDoc load files and convert them to the correct encoding.
Public Class Methods
read_file(filename, encoding, force_transcode = false)
Reads the contents of filename
and handles any encoding
directives in the file.
The content will be converted to the encoding
. If the file
cannot be converted a warning will be printed and nil will be returned.
If force_transcode
is true the document will be transcoded and
any unknown character in the target encoding will be replaced with ‘?’
# File rdoc/encoding.rb, line 19 def self.read_file filename, encoding, force_transcode = false content = open filename, "rb" do |f| f.read end content.gsub!("\r\n", "\n") if RUBY_PLATFORM =~ /mswin|mingw/ utf8 = content.sub!(/\A\xef\xbb\xbf/, '') RDoc::Encoding.set_encoding content if Object.const_defined? :Encoding then begin encoding ||= Encoding.default_external orig_encoding = content.encoding if not orig_encoding.ascii_compatible? then content.encode! encoding elsif utf8 then content.force_encoding Encoding::UTF_8 content.encode! encoding else # assume the content is in our output encoding content.force_encoding encoding end unless content.valid_encoding? then # revert and try to transcode content.force_encoding orig_encoding content.encode! encoding end unless content.valid_encoding? then warn "unable to convert #{filename} to #{encoding}, skipping" content = nil end rescue Encoding::InvalidByteSequenceError, Encoding::UndefinedConversionError => e if force_transcode then content.force_encoding orig_encoding content.encode!(encoding, :invalid => :replace, :undef => :replace, :replace => '?') return content else warn "unable to convert #{e.message} for #{filename}, skipping" return nil end end end content rescue ArgumentError => e raise unless e.message =~ /unknown encoding name - (.*)/ warn "unknown encoding name \"#{$1}\" for #{filename}, skipping" nil rescue Errno::EISDIR, Errno::ENOENT nil end
set_encoding(string)
Sets the encoding of string
based on the magic comment
# File rdoc/encoding.rb, line 79 def self.set_encoding string string =~ /\A(?:#!.*\n)?(.*\n)/ first_line = $1 name = case first_line when /^<\?xml[^?]*encoding=(["'])(.*?)\1/ then $2 when /\b(?:en)?coding[=:]\s*([^\s;]+)/i then $1 else return end string.sub! first_line, '' return unless Object.const_defined? :Encoding enc = Encoding.find name string.force_encoding enc if enc end