From eedd8618910765b7fa92c1f632be0ce6865285d0 Mon Sep 17 00:00:00 2001
From: NAITOH Jun <naitoh@gmail.com>
Date: Tue, 30 Jan 2024 07:35:01 +0900
Subject: [PATCH] Reduce calls to StringScanner.new()

[Why]
StringScanner.new() instances can be reused within parse_attributes, reducing initialization costs.

## 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     11.025      11.202        16.207       17.315 i/s -     100.000 times in 9.069926s 8.926851s 6.170348s 5.775288s
                 sax     30.084      30.519        45.220       47.814 i/s -     100.000 times in 3.324024s 3.276648s 2.211399s 2.091429s
                pull     34.782      35.849        53.867       56.851 i/s -     100.000 times in 2.875069s 2.789495s 1.856439s 1.758998s
              stream     32.546      33.541        46.362       47.775 i/s -     100.000 times in 3.072603s 2.981465s 2.156952s 2.093130s

Comparison:
                              dom
         after(YJIT):        17.3 i/s
        before(YJIT):        16.2 i/s - 1.07x  slower
               after:        11.2 i/s - 1.55x  slower
              before:        11.0 i/s - 1.57x  slower

                              sax
         after(YJIT):        47.8 i/s
        before(YJIT):        45.2 i/s - 1.06x  slower
               after:        30.5 i/s - 1.57x  slower
              before:        30.1 i/s - 1.59x  slower

                             pull
         after(YJIT):        56.9 i/s
        before(YJIT):        53.9 i/s - 1.06x  slower
               after:        35.8 i/s - 1.59x  slower
              before:        34.8 i/s - 1.63x  slower

                           stream
         after(YJIT):        47.8 i/s
        before(YJIT):        46.4 i/s - 1.03x  slower
               after:        33.5 i/s - 1.42x  slower
              before:        32.5 i/s - 1.47x  slower

```

- YJIT=ON : 1.03x - 1.07x faster
- YJIT=OFF : 1.01x - 1.03x faster
---
 lib/rexml/parsers/baseparser.rb | 43 +++++++++++++++++----------------
 1 file changed, 22 insertions(+), 21 deletions(-)

diff --git a/lib/rexml/parsers/baseparser.rb b/lib/rexml/parsers/baseparser.rb
index 7126a12d..0fbb94ee 100644
--- a/lib/rexml/parsers/baseparser.rb
+++ b/lib/rexml/parsers/baseparser.rb
@@ -115,6 +115,7 @@ class BaseParser
       def initialize( source )
         self.stream = source
         @listeners = []
+        @attributes_scanner = StringScanner.new('')
       end
 
       def add_listener( listener )
@@ -601,36 +602,36 @@ def parse_attributes(prefixes, curr_ns)
         return attributes, closed if raw_attributes.nil?
         return attributes, closed if raw_attributes.empty?
 
-        scanner = StringScanner.new(raw_attributes)
-        until scanner.eos?
-          if scanner.scan(/\s+/)
-            break if scanner.eos?
+        @attributes_scanner.string = raw_attributes
+        until @attributes_scanner.eos?
+          if @attributes_scanner.scan(/\s+/)
+            break if @attributes_scanner.eos?
           end
 
-          pos = scanner.pos
+          pos = @attributes_scanner.pos
           loop do
-            break if scanner.scan(ATTRIBUTE_PATTERN)
-            unless scanner.scan(QNAME)
-              message = "Invalid attribute name: <#{scanner.rest}>"
+            break if @attributes_scanner.scan(ATTRIBUTE_PATTERN)
+            unless @attributes_scanner.scan(QNAME)
+              message = "Invalid attribute name: <#{@attributes_scanner.rest}>"
               raise REXML::ParseException.new(message, @source)
             end
-            name = scanner[0]
-            unless scanner.scan(/\s*=\s*/um)
+            name = @attributes_scanner[0]
+            unless @attributes_scanner.scan(/\s*=\s*/um)
               message = "Missing attribute equal: <#{name}>"
               raise REXML::ParseException.new(message, @source)
             end
-            quote = scanner.scan(/['"]/)
+            quote = @attributes_scanner.scan(/['"]/)
             unless quote
               message = "Missing attribute value start quote: <#{name}>"
               raise REXML::ParseException.new(message, @source)
             end
-            unless scanner.scan(/.*#{Regexp.escape(quote)}/um)
+            unless @attributes_scanner.scan(/.*#{Regexp.escape(quote)}/um)
               match_data = @source.match(/^(.*?)(\/)?>/um, true)
               if match_data
-                scanner << "/" if closed
-                scanner << ">"
-                scanner << match_data[1]
-                scanner.pos = pos
+                @attributes_scanner << "/" if closed
+                @attributes_scanner << ">"
+                @attributes_scanner << match_data[1]
+                @attributes_scanner.pos = pos
                 closed = !match_data[2].nil?
                 next
               end
@@ -639,11 +640,11 @@ def parse_attributes(prefixes, curr_ns)
               raise REXML::ParseException.new(message, @source)
             end
           end
-          name = scanner[1]
-          prefix = scanner[2]
-          local_part = scanner[3]
-          # quote = scanner[4]
-          value = scanner[5]
+          name = @attributes_scanner[1]
+          prefix = @attributes_scanner[2]
+          local_part = @attributes_scanner[3]
+          # quote = @attributes_scanner[4]
+          value = @attributes_scanner[5]
           if prefix == "xmlns"
             if local_part == "xml"
               if value != "http://www.w3.org/XML/1998/namespace"