1
0
Fork 0
mirror of https://github.com/ruby/ruby.git synced 2022-11-09 12:17:21 -05:00
ruby--ruby/lib/rexml/source.rb
ser f114b85d89 * Cross-patch from Ruby CVS; mostly Nabu edits.
* Fixes ticket:68.

  ***** Note that this is an API change!!! *****

  NOTE that this involves an API change!  Entity declarations in the doctype now
  generate events that carry two, not one, arguments.

* Implements ticket:15, using gwrite's suggestion.  This allows Element to be
  subclassed.

* Fixed namespaces handling in XPath and element.

  ***** Note that this is an API change!!! *****

  Element.namespaces() now returns a hash of namespace mappings which are
  relevant for that node.

* Fixes a bug in multiple decodings

* The changeset 1230:1231 was bad.  The default behavior is *not* to use the
  native REXML encodings by default, but rather to use ICONV by default.  I'll
  have to think of a better way of managing translations, but the REXML codecs
  are (a) less reliable than ICONV, but more importantly (b) slower.  The real
  solution is to use ICONV by default, but allow users to specify that they
  want to use the pure Ruby codecs.

* Fixes ticket:61 (xpath_parser)

* Fixes ticket:63 (UTF-16; UNILE decoding was bad)

* Improves parsing error messages a little

* Adds the ability to override the encoding detection in Source construction

* Fixes an edge case in Functions::string, where document nodes weren't
  correctly converted

  * Fixes Functions::string() for Element and Document nodes

  * Fixes some problems in entity handling

* Addresses ticket:66

* Fixes ticket:71

* Addresses ticket:78

    NOTE: that this also fixes what is technically another bug in REXML.  REXML's
    XPath parser used to allow exponential notation in numbers.  The XPath spec
    is specific about what a number is, and scientific notation is not included.
    Therefore, this has been fixed.


git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/branches/ruby_1_8@11315 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2006-12-01 02:20:08 +00:00

244 lines
6.4 KiB
Ruby

require 'rexml/encoding'
module REXML
# Generates Source-s. USE THIS CLASS.
class SourceFactory
# Generates a Source object
# @param arg Either a String, or an IO
# @return a Source, or nil if a bad argument was given
def SourceFactory::create_from(arg)
if arg.kind_of? String
Source.new(arg)
elsif arg.respond_to? :read and
arg.respond_to? :readline and
arg.respond_to? :nil? and
arg.respond_to? :eof?
IOSource.new(arg)
elsif arg.kind_of? Source
arg
else
raise "#{source.class} is not a valid input stream. It must walk \n"+
"like either a String, IO, or Source."
end
end
end
# A Source can be searched for patterns, and wraps buffers and other
# objects and provides consumption of text
class Source
include Encoding
# The current buffer (what we're going to read next)
attr_reader :buffer
# The line number of the last consumed text
attr_reader :line
attr_reader :encoding
# Constructor
# @param arg must be a String, and should be a valid XML document
# @param encoding if non-null, sets the encoding of the source to this
# value, overriding all encoding detection
def initialize(arg, encoding=nil)
@orig = @buffer = arg
if encoding
self.encoding = encoding
else
self.encoding = check_encoding( @buffer )
end
@line = 0
end
# Inherited from Encoding
# Overridden to support optimized en/decoding
def encoding=(enc)
return unless super
@line_break = encode( '>' )
if enc != UTF_8
@buffer = decode(@buffer)
@to_utf = true
else
@to_utf = false
end
end
# Scans the source for a given pattern. Note, that this is not your
# usual scan() method. For one thing, the pattern argument has some
# requirements; for another, the source can be consumed. You can easily
# confuse this method. Originally, the patterns were easier
# to construct and this method more robust, because this method
# generated search regexes on the fly; however, this was
# computationally expensive and slowed down the entire REXML package
# considerably, since this is by far the most commonly called method.
# @param pattern must be a Regexp, and must be in the form of
# /^\s*(#{your pattern, with no groups})(.*)/. The first group
# will be returned; the second group is used if the consume flag is
# set.
# @param consume if true, the pattern returned will be consumed, leaving
# everything after it in the Source.
# @return the pattern, if found, or nil if the Source is empty or the
# pattern is not found.
def scan(pattern, cons=false)
return nil if @buffer.nil?
rv = @buffer.scan(pattern)
@buffer = $' if cons and rv.size>0
rv
end
def read
end
def consume( pattern )
@buffer = $' if pattern.match( @buffer )
end
def match_to( char, pattern )
return pattern.match(@buffer)
end
def match_to_consume( char, pattern )
md = pattern.match(@buffer)
@buffer = $'
return md
end
def match(pattern, cons=false)
md = pattern.match(@buffer)
@buffer = $' if cons and md
return md
end
# @return true if the Source is exhausted
def empty?
@buffer == ""
end
def position
@orig.index( @buffer )
end
# @return the current line in the source
def current_line
lines = @orig.split
res = lines.grep @buffer[0..30]
res = res[-1] if res.kind_of? Array
lines.index( res ) if res
end
end
# A Source that wraps an IO. See the Source class for method
# documentation
class IOSource < Source
#attr_reader :block_size
# block_size has been deprecated
def initialize(arg, block_size=500, encoding=nil)
@er_source = @source = arg
@to_utf = false
# Determining the encoding is a deceptively difficult issue to resolve.
# First, we check the first two bytes for UTF-16. Then we
# assume that the encoding is at least ASCII enough for the '>', and
# we read until we get one of those. This gives us the XML declaration,
# if there is one. If there isn't one, the file MUST be UTF-8, as per
# the XML spec. If there is one, we can determine the encoding from
# it.
@buffer = ""
str = @source.read( 2 )
if encoding
self.encoding = encoding
elsif /\A(?:\xfe\xff|\xff\xfe)/n =~ str
self.encoding = check_encoding( str )
else
@line_break = '>'
end
super str+@source.readline( @line_break )
end
def scan(pattern, cons=false)
rv = super
# You'll notice that this next section is very similar to the same
# section in match(), but just a liiittle different. This is
# because it is a touch faster to do it this way with scan()
# than the way match() does it; enough faster to warrent duplicating
# some code
if rv.size == 0
until @buffer =~ pattern or @source.nil?
begin
# READLINE OPT
#str = @source.read(@block_size)
str = @source.readline(@line_break)
str = decode(str) if @to_utf and str
@buffer << str
rescue Iconv::IllegalSequence
raise
rescue
@source = nil
end
end
rv = super
end
rv.taint
rv
end
def read
begin
str = @source.readline(@line_break)
str = decode(str) if @to_utf and str
@buffer << str
rescue Exception, NameError
@source = nil
end
end
def consume( pattern )
match( pattern, true )
end
def match( pattern, cons=false )
rv = pattern.match(@buffer)
@buffer = $' if cons and rv
while !rv and @source
begin
str = @source.readline(@line_break)
str = decode(str) if @to_utf and str
@buffer << str
rv = pattern.match(@buffer)
@buffer = $' if cons and rv
rescue
@source = nil
end
end
rv.taint
rv
end
def empty?
super and ( @source.nil? || @source.eof? )
end
def position
@er_source.stat.pipe? ? 0 : @er_source.pos
end
# @return the current line in the source
def current_line
begin
pos = @er_source.pos # The byte position in the source
lineno = @er_source.lineno # The XML < position in the source
@er_source.rewind
line = 0 # The \r\n position in the source
begin
while @er_source.pos < pos
@er_source.readline
line += 1
end
rescue
end
rescue IOError
pos = -1
line = -1
end
[pos, lineno, line]
end
end
end