mirror of
https://github.com/ruby/ruby.git
synced 2025-08-16 05:59:00 +02:00

http://www.germane-software.com/projects/rexml/ticket/# where '#' is the issue or ticket number. * Fixes ticket:3 (Issue38 in Roundup.) However, this needs further testing. * Fixed a couple of bugs in the SAX2 parser, plus a bunch of other changes I don't remember. * More XPath ordering testing added * Fixed the documentation WRT the raw mode of text nodes (ticket:4) * Fixes roundup issue 43: substring-after bug. See: http://www.germane-software.com/cgi-bin/roundup/rexml/issue43 * Fixed issue44, Element#xpath * Patch submitted by an anonymous doner to allow parsing of Tempfiles. I was hoping that, by now, that whole Source thing would have been changed to use duck typing and avoid this sort of issue... but in the meantime, the patch has been applied. * Fixes ticket:30, XPath default namespace bug. The fix was provided by Lucas Nussbaum. * Aliases #size to #length, as per zdennis's request. * Fixes typo from previous commit * Fixes ticket #32 (and adds a unit test) * Merges a user-contributed patch for issue #40 * Changes Date, Version, and Copyright to upper case, to avoid conflicts with the Date class. * Minor, yet incomplete, documentation changes. * Resolves issue #34 (SAX parser change makes it impossible to parse IO feeds.) * Moves parser.source.position() to parser.position() * Improves the build script (less work for me to package a distribution) git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/branches/ruby_1_8@9776 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
227 lines
5.9 KiB
Ruby
227 lines
5.9 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#, slurp=true
|
|
if arg.kind_of? String
|
|
Source.new(arg)
|
|
elsif arg.kind_of? IO
|
|
IOSource.new(arg)
|
|
elsif arg.kind_of? Source
|
|
arg
|
|
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
|
|
def initialize(arg)
|
|
@orig = @buffer = arg
|
|
self.encoding = check_encoding( @buffer )
|
|
@line = 0
|
|
end
|
|
|
|
# Inherited from Encoding
|
|
# Overridden to support optimized en/decoding
|
|
def encoding=(enc)
|
|
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)
|
|
@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.
|
|
str = @source.read( 2 )
|
|
if (str[0] == 254 && str[1] == 255) || (str[0] == 255 && str[1] == 254)
|
|
@encoding = check_encoding( str )
|
|
@line_break = encode( '>' )
|
|
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
|
|
@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
|