rexml 3.2.8 → 3.2.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: cef1cb55ed6a23bce0af7d46fce791961558ee885c57f1089207deb53e18ff95
-  data.tar.gz: 4fbe36d9e4422d266c2ffee71fab703e6408e9a2b5533ca0ae49411483f98368
+  metadata.gz: ed57404d6f519cb196d671fd629380f5b08a50cf649ae99a71432edceaf15014
+  data.tar.gz: 9097f235049d98aa743998da10724fd6ff5f6cd0cb4f230c59290af4a75e2134
 SHA512:
-  metadata.gz: 60da703f26ff7eaa6cf537634ad68e4c3246605c26c54ea96147fae59bb6c17eeab5c234e5e67301e342472ce8dd3cb671321168cddc212839b9347c8de62f91
-  data.tar.gz: 4d6eeaba460a22bcdc3512ac53504fe87f829cb783069fbebb989fb8f1585fbdfe9ed357c8fbda894fb68777d04f871b9073aa6d13c31eccc6b3b22db10c2ce1
+  metadata.gz: 0d7a0be04c12fcd88c64dd2962d4db49f57ed02c08e3f4628e8e546aea135c672839a19a950423afa72d0cf25af0554558f2261b6b5f2b23637f4ca47d43bd73
+  data.tar.gz: 28479b3b11de58e84f57dc88057f185eb2365998f7fbc9f0df78d5899bb9b241c6bb93d26a57ca1b54d8a058b743daa78a8df52c4ddbfbb5f7c94aeb97724808

data/NEWS.md

@@ -1,5 +1,32 @@
 # News
 
+## 3.2.9 - 2024-06-19 {#version-3-2-9}
+
+### Improvements
+
+  * Added support for old strscan.
+    * GH-132
+    * Reported by Adam
+
+  * Improved attribute value parse performance.
+    * GH-135
+    * Patch by NAITOH Jun.
+
+  * Improved `REXML::Node#each_recursive` performance.
+    * GH-134
+    * GH-139
+    * Patch by Hiroya Fujinami.
+
+  * Improved text parse performance.
+    * Reported by mprogrammer.
+
+### Thanks
+
+  * Adam
+  * NAITOH Jun
+  * Hiroya Fujinami
+  * mprogrammer
+
 ## 3.2.8 - 2024-05-16 {#version-3-2-8}
 
 ### Fixes
@@ -30,7 +57,7 @@
 
   * Improved parse performance when an attribute has many `<`s.
 
-    * GH-124
+    * GH-126
 
 ### Fixes
 
@@ -65,7 +92,6 @@
   * jcavalieri
   * DuKewu
 
-
 ## 3.2.6 - 2023-07-27 {#version-3-2-6}
 
 ### Improvements

data/lib/rexml/node.rb

@@ -52,10 +52,14 @@ module REXML
 
     # Visit all subnodes of +self+ recursively
     def each_recursive(&block) # :yields: node
-      self.elements.each {|node|
-        block.call(node)
-        node.each_recursive(&block)
-      }
+      stack = []
+      each { |child| stack.unshift child if child.node_type == :element }
+      until stack.empty?
+        child = stack.pop
+        yield child
+        n = stack.size
+        child.each { |grandchild| stack.insert n, grandchild if grandchild.node_type == :element }
+      end
     end
 
     # Find (and return) first subnode (recursively) for which the block

data/lib/rexml/parsers/baseparser.rb

@@ -7,6 +7,17 @@ require "strscan"
 
 module REXML
   module Parsers
+    if StringScanner::Version < "3.0.8"
+      module StringScannerCaptures
+        refine StringScanner do
+          def captures
+            values_at(*(1...size))
+          end
+        end
+      end
+      using StringScannerCaptures
+    end
+
     # = Using the Pull Parser
     # <em>This API is experimental, and subject to change.</em>
     #  parser = PullParser.new( "<a>text<b att='val'/>txet</a>" )
@@ -362,6 +373,10 @@ module REXML
         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
@@ -427,8 +442,10 @@ module REXML
               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
@@ -633,8 +650,10 @@ module REXML
               raise REXML::ParseException.new(message, @source)
             end
             quote = match[1]
+            start_position = @source.position
             value = @source.read_until(quote)
             unless value.chomp!(quote)
+              @source.position = start_position
               message = "Missing attribute value end quote: <#{name}>: <#{quote}>"
               raise REXML::ParseException.new(message, @source)
             end

data/lib/rexml/rexml.rb

@@ -31,7 +31,7 @@
 module REXML
   COPYRIGHT = "Copyright © 2001-2008 Sean Russell <ser@germane-software.com>"
   DATE = "2008/019"
-  VERSION = "3.2.8"
+  VERSION = "3.2.9"
   REVISION = ""
 
   Copyright = COPYRIGHT

data/lib/rexml/source.rb

@@ -34,6 +34,16 @@ module REXML
     attr_reader :line
     attr_reader :encoding
 
+    module Private
+      PRE_DEFINED_TERM_PATTERNS = {}
+      pre_defined_terms = ["'", '"', "<"]
+      pre_defined_terms.each do |term|
+        PRE_DEFINED_TERM_PATTERNS[term] = /#{Regexp.escape(term)}/
+      end
+    end
+    private_constant :Private
+    include Private
+
     # Constructor
     # @param arg must be a String, and should be a valid XML document
     # @param encoding if non-null, sets the encoding of the source to this
@@ -69,7 +79,13 @@ module REXML
     end
 
     def read_until(term)
-      @scanner.scan_until(Regexp.union(term)) or @scanner.rest
+      pattern = Private::PRE_DEFINED_TERM_PATTERNS[term] || /#{Regexp.escape(term)}/
+      data = @scanner.scan_until(pattern)
+      unless data
+        data = @scanner.rest
+        @scanner.pos = @scanner.string.bytesize
+      end
+      data
     end
 
     def ensure_buffer
@@ -163,6 +179,7 @@ module REXML
     end
 
     def read(term = nil)
+      term = encode(term) if term
       begin
         @scanner << readline(term)
         true
@@ -173,16 +190,20 @@ module REXML
     end
 
     def read_until(term)
-      pattern = Regexp.union(term)
-      begin
-        until str = @scanner.scan_until(pattern)
-          @scanner << readline(term)
-        end
-      rescue EOFError
-        @scanner.rest
-      else
+      pattern = Private::PRE_DEFINED_TERM_PATTERNS[term] || /#{Regexp.escape(term)}/
+      term = encode(term)
+      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
       end
     end
 

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: rexml
 version: !ruby/object:Gem::Version
-  version: 3.2.8
+  version: 3.2.9
 platform: ruby
 authors:
 - Kouhei Sutou
 bindir: bin
 cert_chain: []
-date: 2024-05-16 00:00:00.000000000 Z
+date: 2024-06-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: strscan
@@ -15,14 +15,14 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 3.0.9
+        version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 3.0.9
+        version: '0'
 description: An XML toolkit for Ruby
 email:
 - kou@cozmixng.org