123456789_123456789_123456789_123456789_123456789_

Class: REXML::Source

Relationships & Source Files
Namespace Children
Modules:
Private
Extension / Inclusion / Inheritance Descendants
Subclasses:
IOSource
Super Chains via Extension / Inclusion / Inheritance
Instance Chain:
self, Encoding
Inherits: Object
Defined in: lib/rexml/source.rb

Overview

A Source can be searched for patterns, and wraps buffers and other objects and provides consumption of text

Class Method Summary

Instance Attribute Summary

Encoding - Included

#encoding

ID —> Encoding name.
#encoding=

Instance Method Summary

Encoding - Included

#decode, #encode, #find_encoding

Constructor Details

.new(arg, encoding = nil) ⇒ Source

Constructor value, overriding all encoding detection

Parameters:

  • arg —

    must be a String, and should be a valid XML document

  • encoding (defaults to: nil) —

    if non-null, sets the encoding of the source to this

[ GitHub ] 

  


# File 'lib/rexml/source.rb', line 71



def initialize(arg, encoding=nil)
  @orig = arg
  @scanner = StringScanner.new(@orig)
  if encoding
    self.encoding = encoding
  else
    detect_encoding
  end
  @line = 0
  @term_encord = {}
end


  







Instance Attribute Details



  

    #buffer_encoding=(encoding)   (writeonly)
  

  [ GitHub ]


  

  


# File 'lib/rexml/source.rb', line 94



def buffer_encoding=(encoding)
  @scanner.string.force_encoding(encoding)
end


  








  

    #empty?  ⇒ Boolean  (readonly)
  



  

    
  





  
Returns:


    
  
  • 
    (Boolean)
—    
    

    true if the Source is exhausted
    

    
  
    • 





  [ GitHub ]


  

  


# File 'lib/rexml/source.rb', line 138



def empty?
  @scanner.eos?
end


  








  

    #encoding   (rw)
  

  [ GitHub ]


  

  


# File 'lib/rexml/source.rb', line 55



attr_reader :encoding


  








  

    #encoding=(enc)   (rw)
  



  

    

Inherited from Encoding Overridden to support optimized en/decoding


  



  [ GitHub ]


  

  


# File 'lib/rexml/source.rb', line 100



def encoding=(enc)
  return unless super
  encoding_updated
end


  








  

    #line   (readonly)
  



  

    

The line number of the last consumed text


  



  [ GitHub ]


  

  


# File 'lib/rexml/source.rb', line 54



attr_reader :line


  








  

    #position   (rw)
  

  [ GitHub ]


  

  


# File 'lib/rexml/source.rb', line 129



def position
  @scanner.pos
end


  








  

    #position=(pos)   (rw)
  

  [ GitHub ]


  

  


# File 'lib/rexml/source.rb', line 133



def position=(pos)
  @scanner.pos = pos
end


  







Instance Method Details



  

    #buffer  
  



  

    

The current buffer (what we’re going to read next)


  



  [ GitHub ]


  

  


# File 'lib/rexml/source.rb', line 84



def buffer
  @scanner.rest
end


  








  

    #current_line  ⇒ Object 
  



  

    
  





  
Returns:


    
  
  • 
    
    
    

    the current line in the source
    

    
  
    • 





  [ GitHub ]


  

  


# File 'lib/rexml/source.rb', line 143



def current_line
  lines = @orig.split
  res = lines.grep @scanner.rest[0..30]
  res = res[-1] if res.kind_of? Array
  lines.index( res ) if res
end


  








  

    #detect_encoding   (private)
  

  [ GitHub ]


  

  


# File 'lib/rexml/source.rb', line 152



def detect_encoding
  scanner_encoding = @scanner.rest.encoding
  detected_encoding = "UTF-8"
  begin
    @scanner.string.force_encoding("ASCII-8BIT")
    if @scanner.scan(/\xfe\xff/n)
      detected_encoding = "UTF-16BE"
    elsif @scanner.scan(/\xff\xfe/n)
      detected_encoding = "UTF-16LE"
    elsif @scanner.scan(/\xef\xbb\xbf/n)
      detected_encoding = "UTF-8"
    end
  ensure
    @scanner.string.force_encoding(scanner_encoding)
  end
  self.encoding = detected_encoding
end


  








  

    #drop_parsed_content  
  

  [ GitHub ]


  

  


# File 'lib/rexml/source.rb', line 88



def drop_parsed_content
  if @scanner.pos > Private::SCANNER_RESET_SIZE
    @scanner.string = @scanner.rest
  end
end


  








  

    #encoding_updated   (private)
  

  [ GitHub ]


  

  


# File 'lib/rexml/source.rb', line 170



def encoding_updated
  if @encoding != 'UTF-8'
    @scanner.string = decode(@scanner.rest)
    @to_utf = true
  else
    @to_utf = false
    @scanner.string.force_encoding(::Encoding::UTF_8)
  end
end


  








  

    #ensure_buffer  
  

  [ GitHub ]


  

  


# File 'lib/rexml/source.rb', line 118



def ensure_buffer
end


  








  

    #match(pattern, cons = false)  
  

  [ GitHub ]


  

  


# File 'lib/rexml/source.rb', line 121



def match(pattern, cons=false)
  if cons
    @scanner.scan(pattern).nil? ? nil : @scanner
  else
    @scanner.check(pattern).nil? ? nil : @scanner
  end
end


  








  

    #read(term = nil)  
  

  [ GitHub ]


  

  


# File 'lib/rexml/source.rb', line 105



def read(term = nil)
end


  








  

    #read_until(term)  
  

  [ GitHub ]


  

  


# File 'lib/rexml/source.rb', line 108



def read_until(term)
  pattern = Private::PRE_DEFINED_TERM_PATTERNS[term] || /#{Regexp.escape(term)}/
  data = @scanner.scan_until(pattern)
  unless data
    data = @scanner.rest
    @scanner.pos = @scanner.string.bytesize
  end
  data
end