From 83ca5c4b0f76cf7b307dd1be1dc934e1e8199863 Mon Sep 17 00:00:00 2001
From: NAITOH Jun <naitoh@gmail.com>
Date: Sun, 21 Jan 2024 06:11:42 +0900
Subject: [PATCH] Reduce calls to `Source#buffer`(`StringScanner#rest`) (#106)

Reduce calls to `Source#buffer`(`StringScanner#rest`)

## Why
`Source#buffer` calling `StringScanner#rest`.
`StringScanner#rest` is slow.
Reduce calls to `Source#buffer`.

## Benchmark

```
RUBYLIB= BUNDLER_ORIG_RUBYLIB= /Users/naitoh/.rbenv/versions/3.3.0/bin/ruby -v -S benchmark-driver /Users/naitoh/ghq/github.com/naitoh/rexml/benchmark/parse.yaml
ruby 3.3.0 (2023-12-25 revision 5124f9ac75) [arm64-darwin22]
Calculating -------------------------------------
                         before       after  before(YJIT)  after(YJIT)
                 dom     10.639      10.985        16.213       16.221 i/s -     100.000 times in 9.399033s 9.103461s 6.167962s 6.164794s
                 sax     28.357      29.440        42.900       44.375 i/s -     100.000 times in 3.526479s 3.396688s 2.331024s 2.253511s
                pull     32.852      34.210        48.976       51.273 i/s -     100.000 times in 3.043965s 2.923140s 2.041816s 1.950344s
              stream     30.821      31.908        43.953       44.697 i/s -     100.000 times in 3.244539s 3.134020s 2.275172s 2.237310s

Comparison:
                              dom
         after(YJIT):        16.2 i/s
        before(YJIT):        16.2 i/s - 1.00x  slower
               after:        11.0 i/s - 1.48x  slower
              before:        10.6 i/s - 1.52x  slower

                              sax
         after(YJIT):        44.4 i/s
        before(YJIT):        42.9 i/s - 1.03x  slower
               after:        29.4 i/s - 1.51x  slower
              before:        28.4 i/s - 1.56x  slower

                             pull
         after(YJIT):        51.3 i/s
        before(YJIT):        49.0 i/s - 1.05x  slower
               after:        34.2 i/s - 1.50x  slower
              before:        32.9 i/s - 1.56x  slower

                           stream
         after(YJIT):        44.7 i/s
        before(YJIT):        44.0 i/s - 1.02x  slower
               after:        31.9 i/s - 1.40x  slower
              before:        30.8 i/s - 1.45x  slower

```

- YJIT=ON : 1.00x - 1.05x faster
- YJIT=OFF : 1.03x - 1.04x faster
---
 lib/rexml/parsers/baseparser.rb | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/lib/rexml/parsers/baseparser.rb b/lib/rexml/parsers/baseparser.rb
index 65bad260..7126a12d 100644
--- a/lib/rexml/parsers/baseparser.rb
+++ b/lib/rexml/parsers/baseparser.rb
@@ -348,9 +348,13 @@ def pull_event
           @source.match(/\A\s*/um, true)
         end
         begin
-          @source.read if @source.buffer.size<2
-          if @source.buffer[0] == ?<
-            if @source.buffer[1] == ?/
+          next_data = @source.buffer
+          if next_data.size < 2
+            @source.read
+            next_data = @source.buffer
+          end
+          if next_data[0] == ?<
+            if next_data[1] == ?/
               @nsstack.shift
               last_tag = @tags.pop
               md = @source.match( CLOSE_MATCH, true )
@@ -364,7 +368,7 @@ def pull_event
                 raise REXML::ParseException.new(message, @source)
               end
               return [ :end_element, last_tag ]
-            elsif @source.buffer[1] == ?!
+            elsif next_data[1] == ?!
               md = @source.match(/\A(\s*[^>]*>)/um)
               #STDERR.puts "SOURCE BUFFER = #{source.buffer}, #{source.buffer.size}"
               raise REXML::ParseException.new("Malformed node", @source) unless md
@@ -383,7 +387,7 @@ def pull_event
               end
               raise REXML::ParseException.new( "Declarations can only occur "+
                 "in the doctype declaration.", @source)
-            elsif @source.buffer[1] == ??
+            elsif next_data[1] == ??
               return process_instruction
             else
               # Get the next tag