diff options
Diffstat (limited to 'lib/rexml/source.rb')
| -rw-r--r-- | lib/rexml/source.rb | 148 |
1 files changed, 97 insertions, 51 deletions
diff --git a/lib/rexml/source.rb b/lib/rexml/source.rb index ce7a2c98b0..af65cf4751 100644 --- a/lib/rexml/source.rb +++ b/lib/rexml/source.rb @@ -1,3 +1,5 @@ +# coding: US-ASCII +# frozen_string_literal: false require 'rexml/encoding' module REXML @@ -7,13 +9,14 @@ module REXML # @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? + if arg.respond_to? :read and + arg.respond_to? :readline and + arg.respond_to? :nil? and + arg.respond_to? :eof? IOSource.new(arg) + elsif arg.respond_to? :to_str + require 'stringio' + IOSource.new(StringIO.new(arg)) elsif arg.kind_of? Source arg else @@ -42,7 +45,7 @@ module REXML if encoding self.encoding = encoding else - self.encoding = check_encoding( @buffer ) + detect_encoding end @line = 0 end @@ -52,22 +55,16 @@ module REXML # 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 + encoding_updated 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 + # to construct and this method more robust, because this method + # generated search regexps 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 @@ -123,6 +120,38 @@ module REXML res = res[-1] if res.kind_of? Array lines.index( res ) if res end + + private + def detect_encoding + buffer_encoding = @buffer.encoding + detected_encoding = "UTF-8" + begin + @buffer.force_encoding("ASCII-8BIT") + if @buffer[0, 2] == "\xfe\xff" + @buffer[0, 2] = "" + detected_encoding = "UTF-16BE" + elsif @buffer[0, 2] == "\xff\xfe" + @buffer[0, 2] = "" + detected_encoding = "UTF-16LE" + elsif @buffer[0, 3] == "\xef\xbb\xbf" + @buffer[0, 3] = "" + detected_encoding = "UTF-8" + end + ensure + @buffer.force_encoding(buffer_encoding) + end + self.encoding = detected_encoding + end + + def encoding_updated + if @encoding != 'UTF-8' + @buffer = decode(@buffer) + @to_utf = true + else + @to_utf = false + @buffer.force_encoding ::Encoding::UTF_8 + end + end end # A Source that wraps an IO. See the Source class for method @@ -134,30 +163,22 @@ module REXML def initialize(arg, block_size=500, encoding=nil) @er_source = @source = arg @to_utf = false + @pending_buffer = nil - # 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 0xfe == str[0] && 0xff == str[1] - @line_break = "\000>" - elsif 0xff == str[0] && 0xfe == str[1] - @line_break = ">\000" - elsif 0xef == str[0] && 0xbb == str[1] - str += @source.read(1) - str = '' if (0xbf == str[2]) - @line_break = ">" + super("", encoding) + else + super(@source.read(3) || "") + end + + if !@to_utf and + @buffer.respond_to?(:force_encoding) and + @source.respond_to?(:external_encoding) and + @source.external_encoding != ::Encoding::UTF_8 + @force_utf8 = true else - @line_break = ">" + @force_utf8 = false end - super str+@source.readline( @line_break ) end def scan(pattern, cons=false) @@ -165,16 +186,12 @@ module REXML # 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 + # than the way match() does it; enough faster to warrant 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 + @buffer << readline rescue Iconv::IllegalSequence raise rescue @@ -189,9 +206,7 @@ module REXML def read begin - str = @source.readline(@line_break) - str = decode(str) if @to_utf and str - @buffer << str + @buffer << readline rescue Exception, NameError @source = nil end @@ -206,9 +221,7 @@ module REXML @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 + @buffer << readline rv = pattern.match(@buffer) @buffer = $' if cons and rv rescue @@ -218,13 +231,13 @@ module REXML rv.taint rv end - + def empty? super and ( @source.nil? || @source.eof? ) end def position - @er_source.stat.pipe? ? 0 : @er_source.pos + @er_source.pos rescue 0 end # @return the current line in the source @@ -247,5 +260,38 @@ module REXML end [pos, lineno, line] end + + private + def readline + str = @source.readline(@line_break) + if @pending_buffer + if str.nil? + str = @pending_buffer + else + str = @pending_buffer + str + end + @pending_buffer = nil + end + return nil if str.nil? + + if @to_utf + decode(str) + else + str.force_encoding(::Encoding::UTF_8) if @force_utf8 + str + end + end + + def encoding_updated + case @encoding + when "UTF-16BE", "UTF-16LE" + @source.binmode + @source.set_encoding(@encoding, @encoding) + end + @line_break = encode(">") + @pending_buffer, @buffer = @buffer, "" + @pending_buffer.force_encoding(@encoding) + super + end end end |