From e06b3fb2660c682423e10d59b92d192c42e9825d Mon Sep 17 00:00:00 2001
From: Sutou Kouhei <kou@clear-code.com>
Date: Fri, 7 Jun 2024 14:34:25 +0900
Subject: [PATCH] Improve text parse performance

If there are many ">"s in text, parsing is very slow.

    Calculating -------------------------------------
                         rexml 3.2.6      master  3.2.6(YJIT)  master(YJIT)
               attribute       1.116      3.618k        1.117        1.941k i/s -      10.000 times in 8.957748s 0.002764s 8.951665s 0.005152s
                    text      27.089      2.262k       42.632        1.033k i/s -      10.000 times in 0.369147s 0.004421s 0.234566s 0.009683s

    Comparison:
                            attribute
                  master:      3617.6 i/s
            master(YJIT):      1941.1 i/s - 1.86x  slower
             3.2.6(YJIT):         1.1 i/s - 3238.31x  slower
             rexml 3.2.6:         1.1 i/s - 3240.51x  slower

                                 text
                  master:      2261.8 i/s
            master(YJIT):      1032.7 i/s - 2.19x  slower
             3.2.6(YJIT):        42.6 i/s - 53.05x  slower
             rexml 3.2.6:        27.1 i/s - 83.49x  slower
---
 benchmark/gt.yaml               | 34 +++++++++++++++++++++++++++++++++
 lib/rexml/parsers/baseparser.rb | 10 ++++++++--
 lib/rexml/source.rb             | 19 +++++++++---------
 3 files changed, 52 insertions(+), 11 deletions(-)
 create mode 100644 benchmark/gt.yaml

diff --git a/benchmark/gt.yaml b/benchmark/gt.yaml
new file mode 100644
index 00000000..3f6af739
--- /dev/null
+++ b/benchmark/gt.yaml
@@ -0,0 +1,34 @@
+loop_count: 10
+contexts:
+  - gems:
+      rexml: 3.2.6
+    require: false
+    prelude: require "rexml"
+  - name: master
+    prelude: |
+      $LOAD_PATH.unshift(File.expand_path("lib"))
+      require "rexml"
+  - name: 3.2.6(YJIT)
+    gems:
+      rexml: 3.2.6
+    require: false
+    prelude: |
+      require "rexml"
+      RubyVM::YJIT.enable
+  - name: master(YJIT)
+    prelude: |
+      $LOAD_PATH.unshift(File.expand_path("lib"))
+      require "rexml"
+      RubyVM::YJIT.enable
+
+prelude: |
+  require "rexml/document"
+
+  n = 10000
+  gts = ">" * n
+  in_attribute = "<test attribute=\"#{gts}\"></test>"
+  in_text = "<test>#{gts}</test>"
+
+benchmark:
+  "attribute": REXML::Document.new(in_attribute)
+  "text":      REXML::Document.new(in_text)
diff --git a/lib/rexml/parsers/baseparser.rb b/lib/rexml/parsers/baseparser.rb
index 82575685..eadc78f7 100644
--- a/lib/rexml/parsers/baseparser.rb
+++ b/lib/rexml/parsers/baseparser.rb
@@ -373,6 +373,10 @@ def pull_event
         begin
           start_position = @source.position
           if @source.match("<", true)
+            # :text's read_until may remain only "<" in buffer. In the
+            # case, buffer is empty here. So we need to fill buffer
+            # here explicitly.
+            @source.ensure_buffer
             if @source.match("/", true)
               @nsstack.shift
               last_tag = @tags.pop
@@ -438,8 +442,10 @@ def pull_event
               return [ :start_element, tag, attributes ]
             end
           else
-            md = @source.match(/([^<]*)/um, true)
-            text = md[1]
+            text = @source.read_until("<")
+            if text.chomp!("<")
+              @source.position -= "<".bytesize
+            end
             return [ :text, text ]
           end
         rescue REXML::UndefinedNamespaceException
diff --git a/lib/rexml/source.rb b/lib/rexml/source.rb
index 542b76a6..982aa84a 100644
--- a/lib/rexml/source.rb
+++ b/lib/rexml/source.rb
@@ -36,7 +36,7 @@ class Source
 
     module Private
       PRE_DEFINED_TERM_PATTERNS = {}
-      pre_defined_terms = ["'", '"']
+      pre_defined_terms = ["'", '"', "<"]
       pre_defined_terms.each do |term|
         PRE_DEFINED_TERM_PATTERNS[term] = /#{Regexp.escape(term)}/
       end
@@ -192,17 +192,18 @@ def read(term = nil)
     def read_until(term)
       pattern = Private::PRE_DEFINED_TERM_PATTERNS[term] || /#{Regexp.escape(term)}/
       term = encode(term)
-      begin
-        until str = @scanner.scan_until(pattern)
-          @scanner << readline(term)
-        end
-      rescue EOFError
+      until str = @scanner.scan_until(pattern)
+        break if @source.nil?
+        break if @source.eof?
+        @scanner << readline(term)
+      end
+      if str
+        read if @scanner.eos? and !@source.eof?
+        str
+      else
         rest = @scanner.rest
         @scanner.pos = @scanner.string.bytesize
         rest
-      else
-        read if @scanner.eos? and !@source.eof?
-        str
       end
     end