rexml 3.3.7 → 3.3.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 1a402bb00d8bf352521fb6ca5354ba92a22d110feedcba40a50e2de5abad277a
-  data.tar.gz: 51f7b5893eef8d8183eb14c719064368029b18c9909b3454047e308c7425ce5b
+  metadata.gz: 9d8de4465de1e9548d66ad026772932f724b9747dc8b1c62960d8efeaeaa8412
+  data.tar.gz: 1cb29aaa36dcef98ba8bd4e9fa249959405f67fdb6bed54d12b466fdf43f57af
 SHA512:
-  metadata.gz: ff091fe421748562931d65301e66dc1d4d313e1c28cce753bc9f31a1f9bac65c0b4939db70117e47f2c3158daa24b708e2519a98a9638114f4e5a1c0d1265e7c
-  data.tar.gz: 720bc72a86eacebbe9a990152d4d0dfcde2e50c71b3fbabaaba44dec91b2f6ff7ca6180b86622cf0ffb36355ab5e5d43f8948e67c70ab4fca1f8bf0882a3585d
+  metadata.gz: 78c881a10f12e46e1b6710d6ec75e42e4311c233376a7587756bc098063d21f52a4d82bcac8201001bf7e39079b3db4015482dae5b4ba46e561ef75fa15b15a0
+  data.tar.gz: 8d7a4b94937ce7b0bdf6ed83152fe207098dfe45333498a64e50d5fe9a686dffa2f66913c1edf265470b2b6a04cfae20857f1cffa404c278249784eeb533d594

data/NEWS.md

@@ -1,5 +1,47 @@
 # News
 
+## 3.3.9 - 2024-10-24 {#version-3-3-9}
+
+### Improvements
+
+  * Improved performance.
+    * GH-210
+    * Patch by NAITOH Jun.
+
+### Fixes
+
+  * Fixed a parse bug for text only invalid XML.
+    * GH-215
+    * Patch by NAITOH Jun.
+
+  * Fixed a parse bug that `&#0x...;` is accepted as a character
+    reference.
+
+### Thanks
+
+  * NAITOH Jun
+
+## 3.3.8 - 2024-09-29 {#version-3-3-8}
+
+### Improvements
+
+  * SAX2: Improve parse performance.
+    * GH-207
+    * Patch by NAITOH Jun.
+
+### Fixes
+
+  * Fixed a bug that unexpected attribute namespace conflict error for
+    the predefined "xml" namespace is reported.
+    * GH-208
+    * Patch by KITAITI Makoto
+
+### Thanks
+
+  * NAITOH Jun
+
+  * KITAITI Makoto
+
 ## 3.3.7 - 2024-09-04 {#version-3-3-7}
 
 ### Improvements

data/lib/rexml/parsers/baseparser.rb

@@ -150,12 +150,13 @@ module REXML
         PEDECL_PATTERN = "\\s+(%)\\s+#{NAME}\\s+#{PEDEF}\\s*>"
         ENTITYDECL_PATTERN = /(?:#{GEDECL_PATTERN})|(?:#{PEDECL_PATTERN})/um
         CARRIAGE_RETURN_NEWLINE_PATTERN = /\r\n?/
-        CHARACTER_REFERENCES = /&#0*((?:\d+)|(?:x[a-fA-F0-9]+));/
+        CHARACTER_REFERENCES = /&#((?:\d+)|(?:x[a-fA-F0-9]+));/
         DEFAULT_ENTITIES_PATTERNS = {}
         default_entities = ['gt', 'lt', 'quot', 'apos', 'amp']
         default_entities.each do |term|
           DEFAULT_ENTITIES_PATTERNS[term] = /&#{term};/
         end
+        XML_PREFIXED_NAMESPACE = "http://www.w3.org/XML/1998/namespace"
       end
       private_constant :Private
 
@@ -166,6 +167,7 @@ module REXML
         @entity_expansion_count = 0
         @entity_expansion_limit = Security.entity_expansion_limit
         @entity_expansion_text_limit = Security.entity_expansion_text_limit
+        @source.ensure_buffer
       end
 
       def add_listener( listener )
@@ -185,7 +187,7 @@ module REXML
         @tags = []
         @stack = []
         @entities = []
-        @namespaces = {}
+        @namespaces = {"xml" => Private::XML_PREFIXED_NAMESPACE}
         @namespaces_restore_stack = []
       end
 
@@ -568,8 +570,12 @@ module REXML
         return rv if matches.size == 0
         rv.gsub!( Private::CHARACTER_REFERENCES ) {
           m=$1
-          m = "0#{m}" if m[0] == ?x
-          [Integer(m)].pack('U*')
+          if m.start_with?("x")
+            code_point = Integer(m[1..-1], 16)
+          else
+            code_point = Integer(m, 10)
+          end
+          [code_point].pack('U*')
         }
         matches.collect!{|x|x[0]}.compact!
         if filter
@@ -790,7 +796,7 @@ module REXML
             @source.match(/\s*/um, true)
             if prefix == "xmlns"
               if local_part == "xml"
-                if value != "http://www.w3.org/XML/1998/namespace"
+                if value != Private::XML_PREFIXED_NAMESPACE
                   msg = "The 'xml' prefix must not be bound to any other namespace "+
                     "(http://www.w3.org/TR/REC-xml-names/#ns-decl)"
                   raise REXML::ParseException.new( msg, @source, self )

data/lib/rexml/parsers/sax2parser.rb

@@ -259,6 +259,8 @@ module REXML
       end
 
       def get_namespace( prefix )
+        return nil if @namespace_stack.empty?
+
         uris = (@namespace_stack.find_all { |ns| not ns[prefix].nil? }) ||
           (@namespace_stack.find { |ns| not ns[nil].nil? })
         uris[-1][prefix] unless uris.nil? or 0 == uris.size

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 = "3.3.7"
+  VERSION = "3.3.9"
   REVISION = ""
 
   Copyright = COPYRIGHT

data/lib/rexml/source.rb

@@ -77,6 +77,7 @@ module REXML
         detect_encoding
       end
       @line = 0
+      @term_encord = {}
     end
 
     # The current buffer (what we're going to read next)
@@ -227,7 +228,7 @@ module REXML
 
     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?
@@ -294,14 +295,19 @@ module REXML
 
     private
     def readline(term = nil)
-      str = @source.readline(term || @line_break)
       if @pending_buffer
+        begin
+          str = @source.readline(term || @line_break)
+        rescue IOError
+        end
         if str.nil?
           str = @pending_buffer
         else
           str = @pending_buffer + str
         end
         @pending_buffer = nil
+      else
+        str = @source.readline(term || @line_break)
       end
       return nil if str.nil?
 

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: rexml
 version: !ruby/object:Gem::Version
-  version: 3.3.7
+  version: 3.3.9
 platform: ruby
 authors:
 - Kouhei Sutou
 bindir: bin
 cert_chain: []
-date: 2024-09-04 00:00:00.000000000 Z
+date: 2024-10-24 00:00:00.000000000 Z
 dependencies: []
 description: An XML toolkit for Ruby
 email:
@@ -102,7 +102,7 @@ homepage: https://github.com/ruby/rexml
 licenses:
 - BSD-2-Clause
 metadata:
-  changelog_uri: https://github.com/ruby/rexml/releases/tag/v3.3.7
+  changelog_uri: https://github.com/ruby/rexml/releases/tag/v3.3.9
 rdoc_options:
 - "--main"
 - README.md