mirror of
https://github.com/ruby/ruby.git
synced 2022-11-09 12:17:21 -05:00
1d8c98a486
http://www.germane-software.com/repos/rexml/tags/3.1.7 r1278@bean: ser | 2007-06-07 00:53:06 -0400 Fixed a double-encoding bug. This was a regression, related to ticket:48. r1292@bean: ser | 2007-07-25 08:19:36 -0400 r1279@bean: ser | 2007-06-09 23:19:02 -0400 Fixes ticket:89 -- encoding CP-1252 was broken. ISO-8859-15 had the same problem. Also in this patch is a fix to merge.rb (unused, but it should at least contain no errors), and a unit test for ticket:88. r1293@bean: ser | 2007-07-25 08:19:37 -0400 r1281@bean: ser | 2007-07-24 11:08:48 -0400 Addresses ticket:85 This is a major rewrite of the XML formatting code. The XML writers have all been extracted out of the classes and put into their own class containers. This makes writing parsers easier, and cleaner. There are three formatters, which correspond to the previous three XML writing modes: REXML::Formatters::Default Prints the XML document exactly as it was parsed REXML::Formatters::Pretty Pretty prints the XML document, destroying whitespace in the document REXML::Formatters::Transitive Pretty prints the XML document, preserving whitespace All of the write() functions have been deprecated (some are still used, but these will also go away) except the write() function on Document, which is left for convenience. To pretty print an XML document the canonical way: formatter = REXML::Formatters::Pretty.new( 5 ) # indent by 5 spaces formatter.write( document, output ) r1294@bean: ser | 2007-07-25 08:19:38 -0400 r1283@bean: ser | 2007-07-24 19:53:30 -0400 This goes with the previous commit. r1295@bean: ser | 2007-07-25 08:19:39 -0400 r1285@bean: ser | 2007-07-24 20:02:07 -0400 And THIS goes with the previous two patches. Dammit. r1296@bean: ser | 2007-07-25 08:19:40 -0400 r1287@bean: ser | 2007-07-24 20:12:25 -0400 Applied patch from Jeff Barczewski. Note that this changes what the values of the name and IDs are from the previous behavior -- the values no longer include the quotes. This is the correct behavior, so I'm leaving it in, but it is not backwards compatible. Also fixes the serializer so that it outputs the doctype in a correct format (needed as a result of this change). r1297@bean: ser | 2007-07-25 08:38:38 -0400 Version update git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@12844 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
247 lines
7 KiB
Ruby
247 lines
7 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 )
|
|
elsif (0xef == str[0] && 0xbb == str[1])
|
|
str += @source.read(1)
|
|
str = '' if (0xbf == str[2])
|
|
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
|