Add Source#skip_spaces method

## Why?
In the case of `@source.match?(/\s+/um, true)`, if there are no spaces at the beginning, I want to stop reading immediately.
However, it continues to read the buffer until it finds a match, but it never finds a match.
As a result, it continues reading until the end of the file.

In the case of large XML files, drop_parsed_content occur frequently until the buffer is cleared, which may affect performance.

Author: naitoh

lib/rexml/parsers/baseparser.rb

@@ -280,7 +280,7 @@ def pull_event
               return [ :comment, process_comment ]
             elsif @source.match?("DOCTYPE", true)
               base_error_message = "Malformed DOCTYPE"
-              unless @source.match?(/\s+/um, true)
+              unless @source.skip_spaces
                 if @source.match?(">")
                   message = "#{base_error_message}: name is missing"
                 else
@@ -290,7 +290,7 @@ def pull_event
                 raise REXML::ParseException.new(message, @source)
               end
               name = parse_name(base_error_message)
-              @source.match?(/\s*/um, true) # skip spaces
+              @source.skip_spaces
               if @source.match?("[", true)
                 id = [nil, nil, nil]
                 @document_status = :in_doctype
@@ -306,7 +306,7 @@ def pull_event
                   # For backward compatibility
                   id[1], id[2] = id[2], nil
                 end
-                @source.match?(/\s*/um, true) # skip spaces
+                @source.skip_spaces
                 if @source.match?("[", true)
                   @document_status = :in_doctype
                 elsif @source.match?(">", true)
@@ -319,7 +319,7 @@ def pull_event
               end
               args = [:start_doctype, name, *id]
               if @document_status == :after_doctype
-                @source.match?(/\s*/um, true)
+                @source.skip_spaces
                 @stack << [ :end_doctype ]
               end
               return args
@@ -330,7 +330,7 @@ def pull_event
           end
         end
         if @document_status == :in_doctype
-          @source.match?(/\s*/um, true) # skip spaces
+          @source.skip_spaces
           start_position = @source.position
           if @source.match?("<!", true)
             if @source.match?("ELEMENT", true)
@@ -391,7 +391,7 @@ def pull_event
               return [ :attlistdecl, element, pairs, contents ]
             elsif @source.match?("NOTATION", true)
               base_error_message = "Malformed notation declaration"
-              unless @source.match?(/\s+/um, true)
+              unless @source.skip_spaces
                 if @source.match?(">")
                   message = "#{base_error_message}: name is missing"
                 else
@@ -404,7 +404,7 @@ def pull_event
               id = parse_id(base_error_message,
                             accept_external_id: true,
                             accept_public_id: true)
-              @source.match?(/\s*/um, true) # skip spaces
+              @source.skip_spaces
               unless @source.match?(">", true)
                 message = "#{base_error_message}: garbage before end >"
                 raise REXML::ParseException.new(message, @source)
@@ -425,7 +425,7 @@ def pull_event
           end
         end
         if @document_status == :after_doctype
-          @source.match?(/\s*/um, true)
+          @source.skip_spaces
         end
         begin
           start_position = @source.position
@@ -735,7 +735,7 @@ def process_comment
 
       def process_instruction
         name = parse_name("Malformed XML: Invalid processing instruction node")
-        if @source.match?(/\s+/um, true)
+        if @source.skip_spaces
           match_data = @source.match(/(.*?)\?>/um, true)
           unless match_data
             raise ParseException.new("Malformed XML: Unclosed processing instruction", @source)
@@ -817,7 +817,7 @@ def parse_attributes(prefixes)
               message = "Missing attribute value end quote: <#{name}>: <#{quote}>"
               raise REXML::ParseException.new(message, @source)
             end
-            @source.match?(/\s*/um, true)
+            @source.skip_spaces
             if prefix == "xmlns"
               if local_part == "xml"
                 if value != Private::XML_PREFIXED_NAMESPACE

lib/rexml/source.rb

@@ -65,6 +65,7 @@ class Source
     attr_reader :encoding
 
     module Private
+      SPACES_PATTERN = /\s+/um
       SCANNER_RESET_SIZE = 100000
       PRE_DEFINED_TERM_PATTERNS = {}
       pre_defined_terms = ["'", '"', "<", "]]>"]
@@ -150,6 +151,10 @@ def match?(pattern, cons=false)
       end
     end
 
+    def skip_spaces
+      @scanner.skip(Private::SPACES_PATTERN) ? true : false
+    end
+
     def position
       @scanner.pos
     end

test/parse/test_document_type_declaration.rb

@@ -49,10 +49,10 @@ def test_no_name
         end
         assert_equal(<<-DETAIL.chomp, exception.to_s)
 Malformed DOCTYPE: name is missing
-Line: 3
-Position: 17
+Line: 1
+Position: 10
 Last 80 unconsumed characters:
-<!DOCTYPE>  <r/> 
+<!DOCTYPE>
         DETAIL
       end
     end