Optimize IOSource#read_until method (#210)

## Why? The result of `encode(term)` can be cached. ## Benchmark ``` RUBYLIB= BUNDLER_ORIG_RUBYLIB= /Users/naitoh/.rbenv/versions/3.3.4/bin/ruby -v -S benchmark-driver /Users/naitoh/ghq/github.com/naitoh/rexml/benchmark/parse.yaml ruby 3.3.4 (2024-07-09 revision be1089c8ec) [arm64-darwin22] Calculating ------------------------------------- before after before(YJIT) after(YJIT) dom 17.546 18.512 32.282 32.306 i/s - 100.000 times in 5.699323s 5.402026s 3.097658s 3.095448s sax 25.435 28.294 47.526 50.074 i/s - 100.000 times in 3.931613s 3.534310s 2.104122s 1.997057s pull 29.471 31.870 54.400 57.554 i/s - 100.000 times in 3.393211s 3.137793s 1.838222s 1.737494s stream 29.169 31.153 51.613 52.898 i/s - 100.000 times in 3.428318s 3.209941s 1.937508s 1.890424s Comparison: dom after(YJIT): 32.3 i/s before(YJIT): 32.3 i/s - 1.00x slower after: 18.5 i/s - 1.75x slower before: 17.5 i/s - 1.84x slower sax after(YJIT): 50.1 i/s before(YJIT): 47.5 i/s - 1.05x slower after: 28.3 i/s - 1.77x slower before: 25.4 i/s - 1.97x slower pull after(YJIT): 57.6 i/s before(YJIT): 54.4 i/s - 1.06x slower after: 31.9 i/s - 1.81x slower before: 29.5 i/s - 1.95x slower stream after(YJIT): 52.9 i/s before(YJIT): 51.6 i/s - 1.02x slower after: 31.2 i/s - 1.70x slower before: 29.2 i/s - 1.81x slower ``` - YJIT=ON : 1.00x - 1.06x faster - YJIT=OFF : 1.05x - 1.11x faster

Author: naitoh

lib/rexml/source.rb

@@ -77,6 +77,7 @@ def initialize(arg, encoding=nil)
  detect_encoding
  end
  @line = 0
+ @term_encord = {}
  end
 
  # The current buffer (what we're going to read next)
@@ -227,7 +228,7 @@ def read(term = nil, min_bytes = 1)
 
  def read_until(term)
  pattern = Private::PRE_DEFINED_TERM_PATTERNS[term] || /#{Regexp.escape(term)}/
- term = encode(term)
+ term = @term_encord[term] ||= encode(term)
  until str = @scanner.scan_until(pattern)
  break if @source.nil?
  break if @source.eof?

test/test_document.rb

@@ -403,6 +403,40 @@ def test_utf_16
  assert_equal(expected_xml, actual_xml)
  end
  end
+
+ class ReadUntilTest < Test::Unit::TestCase
+ def test_utf_8
+ xml = <<-EOX.force_encoding("ASCII-8BIT")
+<?xml version="1.0" encoding="UTF-8"?>
+<message testing=">">Hello world!</message>
+EOX
+ document = REXML::Document.new(xml)
+ assert_equal("UTF-8", document.encoding)
+ assert_equal(">", REXML::XPath.match(document, "/message")[0].attribute("testing").value)
+ end
+
+ def test_utf_16le
+ xml = <<-EOX.encode("UTF-16LE").force_encoding("ASCII-8BIT")
+<?xml version="1.0" encoding="UTF-16"?>
+<message testing=">">Hello world!</message>
+EOX
+ bom = "\ufeff".encode("UTF-16LE").force_encoding("ASCII-8BIT")
+ document = REXML::Document.new(bom + xml)
+ assert_equal("UTF-16", document.encoding)
+ assert_equal(">", REXML::XPath.match(document, "/message")[0].attribute("testing").value)
+ end
+
+ def test_utf_16be
+ xml = <<-EOX.encode("UTF-16BE").force_encoding("ASCII-8BIT")
+<?xml version="1.0" encoding="UTF-16"?>
+<message testing=">">Hello world!</message>
+EOX
+ bom = "\ufeff".encode("UTF-16BE").force_encoding("ASCII-8BIT")
+ document = REXML::Document.new(bom + xml)
+ assert_equal("UTF-16", document.encoding)
+ assert_equal(">", REXML::XPath.match(document, "/message")[0].attribute("testing").value)
+ end
+ end
  end
  end
 end