Update processing of @document_status == :in_doctype to StringScann…

…er style [Changed] Of the `intSubset` of DOCTYPE, "<!" added consideration for processing `Comments` that begin with "<!". [Spec] https://www.w3.org/TR/2006/REC-xml11-20060816/#NT-doctypedecl > [28] doctypedecl ::= '<!DOCTYPE' S Name (S ExternalID)? S? ('[' intSubset ']' S?)? '>' https://www.w3.org/TR/2006/REC-xml11-20060816/#NT-intSubset > [28b] intSubset ::= (markupdecl | DeclSep)* https://www.w3.org/TR/2006/REC-xml11-20060816/#NT-markupdecl > [29] markupdecl ::= elementdecl | AttlistDecl | EntityDecl | NotationDecl | PI | Comment https://www.w3.org/TR/2006/REC-xml11-20060816/#NT-elementdecl > [45] elementdecl ::= '<!ELEMENT' S Name S contentspec S? '>' https://www.w3.org/TR/2006/REC-xml11-20060816/#NT-AttlistDecl > [52] AttlistDecl ::= '<!ATTLIST' S Name AttDef* S? '>' https://www.w3.org/TR/2006/REC-xml11-20060816/#NT-EntityDecl > [70] EntityDecl ::= GEDecl | PEDecl > [71] GEDecl ::= '<!ENTITY' S Name S EntityDef S? '>' > [72] PEDecl ::= '<!ENTITY' S '%' S Name S PEDef S? '>' https://www.w3.org/TR/2006/REC-xml11-20060816/#NT-NotationDecl > [82] NotationDecl ::= '<!NOTATION' S Name S (ExternalID | PublicID) S? '>' https://www.w3.org/TR/2006/REC-xml11-20060816/#NT-PI > [16] PI ::= '<?' PITarget (S (Char* - (Char* '?>' Char*)))? '?>' https://www.w3.org/TR/2006/REC-xml11-20060816/#NT-Comment > [15] Comment ::= '' https://www.w3.org/TR/2006/REC-xml11-20060816/#NT-DeclSep > [28a] DeclSep ::= PEReference | S https://www.w3.org/TR/2006/REC-xml11-20060816/#NT-PEReference > [69] PEReference ::= '%' Name ';' [Benchmark] ``` RUBYLIB= BUNDLER_ORIG_RUBYLIB= N_ELEMENTS=500 N_ATTRIBUTES=1 /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 118.316 121.880 182.080 192.754 i/s - 100.000 times in 0.845194s 0.820481s 0.549208s 0.518795s sax 362.797 370.424 557.308 598.347 i/s - 100.000 times in 0.275636s 0.269961s 0.179434s 0.167127s pull 436.479 445.266 689.066 755.002 i/s - 100.000 times in 0.229106s 0.224585s 0.145124s 0.132450s stream 449.029 465.134 643.141 727.357 i/s - 100.000 times in 0.222703s 0.214992s 0.155487s 0.137484s Comparison: dom after(YJIT): 192.8 i/s before(YJIT): 182.1 i/s - 1.06x slower after: 121.9 i/s - 1.58x slower before: 118.3 i/s - 1.63x slower sax after(YJIT): 598.3 i/s before(YJIT): 557.3 i/s - 1.07x slower after: 370.4 i/s - 1.62x slower before: 362.8 i/s - 1.65x slower pull after(YJIT): 755.0 i/s before(YJIT): 689.1 i/s - 1.10x slower after: 445.3 i/s - 1.70x slower before: 436.5 i/s - 1.73x slower stream after(YJIT): 727.4 i/s before(YJIT): 643.1 i/s - 1.13x slower after: 465.1 i/s - 1.56x slower before: 449.0 i/s - 1.62x slower ``` - YJIT=ON : 1.06x - 1.13x faster - YJIT=OFF : 1.02x - 1.03x faster
ruby · Feb 25, 2024 · 8d7fc13 · 8d7fc13
1 parent 9a075bf
commit 8d7fc13
Showing 1 changed file with 74 additions and 66 deletions.
diff --git a/lib/rexml/parsers/baseparser.rb b/lib/rexml/parsers/baseparser.rb
@@ -251,76 +251,84 @@ def pull_event
         if @document_status == :in_doctype
           @source.read
           @source.match(/\s*/um, true, false) # skip spaces
-          if match = @source.match( /(%.*?;)\s*$/um, true, false)
-            return [ :externalentity, match[1] ]
-          elsif match = @source.match(/(<!ELEMENT.*?)>/um, true, false)
-            return [ :elementdecl, match[1] ]
-          elsif @source.match( "<!ENTITY", true, false)
-            match = [:entitydecl, *@source.match( ENTITYDECL, true ).captures.compact]
-            ref = false
-            if match[1] == '%'
-              ref = true
-              match.delete_at 1
-            end
-            # Now we have to sort out what kind of entity reference this is
-            if match[2] == 'SYSTEM'
-              # External reference
-              match[3] = match[3][1..-2] # PUBID
-              match.delete_at(4) if match.size > 4 # Chop out NDATA decl
-              # match is [ :entity, name, SYSTEM, pubid(, ndata)? ]
-            elsif match[2] == 'PUBLIC'
-              # External reference
-              match[3] = match[3][1..-2] # PUBID
-              match[4] = match[4][1..-2] # HREF
-              match.delete_at(5) if match.size > 5 # Chop out NDATA decl
-              # match is [ :entity, name, PUBLIC, pubid, href(, ndata)? ]
-            else
-              match[2] = match[2][1..-2]
-              match.pop if match.size == 4
-              # match is [ :entity, name, value ]
-            end
-            match << '%' if ref
-            return match
-          elsif @source.match( "<!ATTLIST", true, false)
-            md = @source.match( ATTLISTDECL_PATTERN, true )
-            raise REXML::ParseException.new( "Bad ATTLIST declaration!", @source ) if md.nil?
-            element = md[1]
-            contents = md[0]
-
-            pairs = {}
-            values = md[0].scan( ATTDEF_RE )
-            values.each do |attdef|
-              unless attdef[3] == "#IMPLIED"
-                attdef.compact!
-                val = attdef[3]
-                val = attdef[4] if val == "#FIXED "
-                pairs[attdef[0]] = val
-                if attdef[0] =~ /^xmlns:(.*)/
-                  @nsstack[0] << $1
-                end
+          if match = @source.match("<!", true, false)
+            if match = @source.match(/(ELEMENT.*?)>/um, true, false)
+              return [ :elementdecl, "<!" + match[1] ]
+            elsif @source.match( "ENTITY", true, false)
+              match = [:entitydecl, *@source.match( ENTITYDECL, true ).captures.compact]
+              ref = false
+              if match[1] == '%'
+                ref = true
+                match.delete_at 1
               end
-            end
-            return [ :attlistdecl, element, pairs, contents ]
-          elsif @source.match( "<!NOTATION", true, false)
-            base_error_message = "Malformed notation declaration"
-            unless @source.match(/\s+/um, true)
-              if @source.match(/\s*>/um)
-                message = "#{base_error_message}: name is missing"
+              # Now we have to sort out what kind of entity reference this is
+              if match[2] == 'SYSTEM'
+                # External reference
+                match[3] = match[3][1..-2] # PUBID
+                match.delete_at(4) if match.size > 4 # Chop out NDATA decl
+                # match is [ :entity, name, SYSTEM, pubid(, ndata)? ]
+              elsif match[2] == 'PUBLIC'
+                # External reference
+                match[3] = match[3][1..-2] # PUBID
+                match[4] = match[4][1..-2] # HREF
+                match.delete_at(5) if match.size > 5 # Chop out NDATA decl
+                # match is [ :entity, name, PUBLIC, pubid, href(, ndata)? ]
               else
-                message = "#{base_error_message}: invalid declaration name"
+                match[2] = match[2][1..-2]
+                match.pop if match.size == 4
+                # match is [ :entity, name, value ]
               end
-              @source.string = " <!NOTATION" + @source.buffer
-              raise REXML::ParseException.new(message, @source)
-            end
-            name = parse_name(base_error_message)
-            id = parse_id(base_error_message,
-                          accept_external_id: true,
-                          accept_public_id: true)
-            unless @source.match(/\s*>/um, true)
-              message = "#{base_error_message}: garbage before end >"
-              raise REXML::ParseException.new(message, @source)
+              match << '%' if ref
+              return match
+            elsif @source.match( "ATTLIST", true, false)
+              md = @source.match( ATTLISTDECL_PATTERN, true )
+              raise REXML::ParseException.new( "Bad ATTLIST declaration!", @source ) if md.nil?
+              element = md[1]
+              contents = md[0]
+
+              pairs = {}
+              values = md[0].scan( ATTDEF_RE )
+              values.each do |attdef|
+                unless attdef[3] == "#IMPLIED"
+                  attdef.compact!
+                  val = attdef[3]
+                  val = attdef[4] if val == "#FIXED "
+                  pairs[attdef[0]] = val
+                  if attdef[0] =~ /^xmlns:(.*)/
+                    @nsstack[0] << $1
+                  end
+                end
+              end
+              return [ :attlistdecl, element, pairs, contents ]
+            elsif @source.match( "NOTATION", true, false)
+              base_error_message = "Malformed notation declaration"
+              unless @source.match(/\s+/um, true)
+                if @source.match(/\s*>/um)
+                  message = "#{base_error_message}: name is missing"
+                else
+                  message = "#{base_error_message}: invalid declaration name"
+                end
+                @source.string = " <!NOTATION" + @source.buffer
+                raise REXML::ParseException.new(message, @source)
+              end
+              name = parse_name(base_error_message)
+              id = parse_id(base_error_message,
+                            accept_external_id: true,
+                            accept_public_id: true)
+              unless @source.match(/\s*>/um, true)
+                message = "#{base_error_message}: garbage before end >"
+                raise REXML::ParseException.new(message, @source)
+              end
+              return [:notationdecl, name, *id]
+            elsif md = @source.match( /--(.*?)-->/um, true, false)
+              case md[1]
+              when /--/, /-\z/
+                raise REXML::ParseException.new("Malformed comment", @source)
+              end
+              return [ :comment, md[1] ] if md
             end
-            return [:notationdecl, name, *id]
+          elsif match = @source.match( /(%.*?;)\s*$/um, true, false)
+            return [ :externalentity, match[1] ]
           elsif @source.match( /\]\s*>/um, true, false)
             @document_status = :after_doctype
             return [ :end_doctype ]