diff options
Diffstat (limited to 'lib/rexml/parsers')
| -rw-r--r-- | lib/rexml/parsers/baseparser.rb | 761 | ||||
| -rw-r--r-- | lib/rexml/parsers/pullparser.rb | 318 | ||||
| -rw-r--r-- | lib/rexml/parsers/sax2parser.rb | 7 | ||||
| -rw-r--r-- | lib/rexml/parsers/streamparser.rb | 74 | ||||
| -rw-r--r-- | lib/rexml/parsers/treeparser.rb | 10 |
5 files changed, 597 insertions, 573 deletions
diff --git a/lib/rexml/parsers/baseparser.rb b/lib/rexml/parsers/baseparser.rb index e95cba8904..bce4ba4c20 100644 --- a/lib/rexml/parsers/baseparser.rb +++ b/lib/rexml/parsers/baseparser.rb @@ -2,103 +2,103 @@ require 'rexml/parseexception' require 'rexml/source' module REXML - module Parsers - # = Using the Pull Parser - # <em>This API is experimental, and subject to change.</em> - # parser = PullParser.new( "<a>text<b att='val'/>txet</a>" ) - # while parser.has_next? - # res = parser.next - # puts res[1]['att'] if res.start_tag? and res[0] == 'b' - # end - # See the PullEvent class for information on the content of the results. - # The data is identical to the arguments passed for the various events to - # the StreamListener API. - # - # Notice that: - # parser = PullParser.new( "<a>BAD DOCUMENT" ) - # while parser.has_next? - # res = parser.next - # raise res[1] if res.error? - # end - # - # Nat Price gave me some good ideas for the API. - class BaseParser - NCNAME_STR= '[\w:][\-\w\d.]*' - NAME_STR= "(?:#{NCNAME_STR}:)?#{NCNAME_STR}" + module Parsers + # = Using the Pull Parser + # <em>This API is experimental, and subject to change.</em> + # parser = PullParser.new( "<a>text<b att='val'/>txet</a>" ) + # while parser.has_next? + # res = parser.next + # puts res[1]['att'] if res.start_tag? and res[0] == 'b' + # end + # See the PullEvent class for information on the content of the results. + # The data is identical to the arguments passed for the various events to + # the StreamListener API. + # + # Notice that: + # parser = PullParser.new( "<a>BAD DOCUMENT" ) + # while parser.has_next? + # res = parser.next + # raise res[1] if res.error? + # end + # + # Nat Price gave me some good ideas for the API. + class BaseParser + NCNAME_STR= '[\w:][\-\w\d.]*' + NAME_STR= "(?:#{NCNAME_STR}:)?#{NCNAME_STR}" - NAMECHAR = '[\-\w\d\.:]' - NAME = "([\\w:]#{NAMECHAR}*)" - NMTOKEN = "(?:#{NAMECHAR})+" - NMTOKENS = "#{NMTOKEN}(\\s+#{NMTOKEN})*" - REFERENCE = "(?:&#{NAME};|&#\\d+;|&#x[0-9a-fA-F]+;)" - REFERENCE_RE = /#{REFERENCE}/ + NAMECHAR = '[\-\w\d\.:]' + NAME = "([\\w:]#{NAMECHAR}*)" + NMTOKEN = "(?:#{NAMECHAR})+" + NMTOKENS = "#{NMTOKEN}(\\s+#{NMTOKEN})*" + REFERENCE = "(?:&#{NAME};|&#\\d+;|&#x[0-9a-fA-F]+;)" + REFERENCE_RE = /#{REFERENCE}/ - DOCTYPE_START = /\A\s*<!DOCTYPE\s/um - DOCTYPE_PATTERN = /\s*<!DOCTYPE\s+(.*?)(\[|>)/um - ATTRIBUTE_PATTERN = /\s*(#{NAME_STR})\s*=\s*(["'])(.*?)\2/um - COMMENT_START = /\A<!--/u - COMMENT_PATTERN = /<!--(.*?)-->/um - CDATA_START = /\A<!\[CDATA\[/u - CDATA_END = /^\s*\]\s*>/um - CDATA_PATTERN = /<!\[CDATA\[(.*?)\]\]>/um - XMLDECL_START = /\A<\?xml\s/u; - XMLDECL_PATTERN = /<\?xml\s+(.*?)\?>*/um - INSTRUCTION_START = /\A<\?/u - INSTRUCTION_PATTERN = /<\?(.*?)(\s+.*?)?\?>/um - TAG_MATCH = /^<((?>#{NAME_STR}))\s*((?>\s+#{NAME_STR}\s*=\s*(["']).*?\3)*)\s*(\/)?>/um - CLOSE_MATCH = /^\s*<\/(#{NAME_STR})\s*>/um + DOCTYPE_START = /\A\s*<!DOCTYPE\s/um + DOCTYPE_PATTERN = /\s*<!DOCTYPE\s+(.*?)(\[|>)/um + ATTRIBUTE_PATTERN = /\s*(#{NAME_STR})\s*=\s*(["'])(.*?)\2/um + COMMENT_START = /\A<!--/u + COMMENT_PATTERN = /<!--(.*?)-->/um + CDATA_START = /\A<!\[CDATA\[/u + CDATA_END = /^\s*\]\s*>/um + CDATA_PATTERN = /<!\[CDATA\[(.*?)\]\]>/um + XMLDECL_START = /\A<\?xml\s/u; + XMLDECL_PATTERN = /<\?xml\s+(.*?)\?>/um + INSTRUCTION_START = /\A<\?/u + INSTRUCTION_PATTERN = /<\?(.*?)(\s+.*?)?\?>/um + TAG_MATCH = /^<((?>#{NAME_STR}))\s*((?>\s+#{NAME_STR}\s*=\s*(["']).*?\3)*)\s*(\/)?>/um + CLOSE_MATCH = /^\s*<\/(#{NAME_STR})\s*>/um - VERSION = /\bversion\s*=\s*["'](.*?)['"]/um - ENCODING = /\bencoding=["'](.*?)['"]/um - STANDALONE = /\bstandalone=["'](.*?)['"]/um + VERSION = /\bversion\s*=\s*["'](.*?)['"]/um + ENCODING = /\bencoding=["'](.*?)['"]/um + STANDALONE = /\bstandalone=["'](.*?)['"]/um - ENTITY_START = /^\s*<!ENTITY/ - IDENTITY = /^([!\*\w\-]+)(\s+#{NCNAME_STR})?(\s+["'].*?['"])?(\s+['"].*?["'])?/u - ELEMENTDECL_START = /^\s*<!ELEMENT/um - ELEMENTDECL_PATTERN = /^\s*(<!ELEMENT.*?)>/um - SYSTEMENTITY = /^\s*(%.*?;)\s*$/um - ENUMERATION = "\\(\\s*#{NMTOKEN}(?:\\s*\\|\\s*#{NMTOKEN})*\\s*\\)" - NOTATIONTYPE = "NOTATION\\s+\\(\\s*#{NAME}(?:\\s*\\|\\s*#{NAME})*\\s*\\)" - ENUMERATEDTYPE = "(?:(?:#{NOTATIONTYPE})|(?:#{ENUMERATION}))" - ATTTYPE = "(CDATA|ID|IDREF|IDREFS|ENTITY|ENTITIES|NMTOKEN|NMTOKENS|#{ENUMERATEDTYPE})" - ATTVALUE = "(?:\"((?:[^<&\"]|#{REFERENCE})*)\")|(?:'((?:[^<&']|#{REFERENCE})*)')" - DEFAULTDECL = "(#REQUIRED|#IMPLIED|(?:(#FIXED\\s+)?#{ATTVALUE}))" - ATTDEF = "\\s+#{NAME}\\s+#{ATTTYPE}\\s+#{DEFAULTDECL}" - ATTDEF_RE = /#{ATTDEF}/ - ATTLISTDECL_START = /^\s*<!ATTLIST/um - ATTLISTDECL_PATTERN = /^\s*<!ATTLIST\s+#{NAME}(?:#{ATTDEF})*\s*>/um - NOTATIONDECL_START = /^\s*<!NOTATION/um - PUBLIC = /^\s*<!NOTATION\s+(\w[\-\w]*)\s+(PUBLIC)\s+((["']).*?\4)\s*>/um - SYSTEM = /^\s*<!NOTATION\s+(\w[\-\w]*)\s+(SYSTEM)\s+((["']).*?\4)\s*>/um + ENTITY_START = /^\s*<!ENTITY/ + IDENTITY = /^([!\*\w\-]+)(\s+#{NCNAME_STR})?(\s+["'].*?['"])?(\s+['"].*?["'])?/u + ELEMENTDECL_START = /^\s*<!ELEMENT/um + ELEMENTDECL_PATTERN = /^\s*(<!ELEMENT.*?)>/um + SYSTEMENTITY = /^\s*(%.*?;)\s*$/um + ENUMERATION = "\\(\\s*#{NMTOKEN}(?:\\s*\\|\\s*#{NMTOKEN})*\\s*\\)" + NOTATIONTYPE = "NOTATION\\s+\\(\\s*#{NAME}(?:\\s*\\|\\s*#{NAME})*\\s*\\)" + ENUMERATEDTYPE = "(?:(?:#{NOTATIONTYPE})|(?:#{ENUMERATION}))" + ATTTYPE = "(CDATA|ID|IDREF|IDREFS|ENTITY|ENTITIES|NMTOKEN|NMTOKENS|#{ENUMERATEDTYPE})" + ATTVALUE = "(?:\"((?:[^<&\"]|#{REFERENCE})*)\")|(?:'((?:[^<&']|#{REFERENCE})*)')" + DEFAULTDECL = "(#REQUIRED|#IMPLIED|(?:(#FIXED\\s+)?#{ATTVALUE}))" + ATTDEF = "\\s+#{NAME}\\s+#{ATTTYPE}\\s+#{DEFAULTDECL}" + ATTDEF_RE = /#{ATTDEF}/ + ATTLISTDECL_START = /^\s*<!ATTLIST/um + ATTLISTDECL_PATTERN = /^\s*<!ATTLIST\s+#{NAME}(?:#{ATTDEF})*\s*>/um + NOTATIONDECL_START = /^\s*<!NOTATION/um + PUBLIC = /^\s*<!NOTATION\s+(\w[\-\w]*)\s+(PUBLIC)\s+(["'])(.*?)\3(?:\s+(["'])(.*?)\5)?\s*>/um + SYSTEM = /^\s*<!NOTATION\s+(\w[\-\w]*)\s+(SYSTEM)\s+(["'])(.*?)\3\s*>/um - TEXT_PATTERN = /\A([^<]*)/um + TEXT_PATTERN = /\A([^<]*)/um - # Entity constants - PUBIDCHAR = "\x20\x0D\x0Aa-zA-Z0-9\\-()+,./:=?;!*@$_%#" - SYSTEMLITERAL = %Q{((?:"[^"]*")|(?:'[^']*'))} - PUBIDLITERAL = %Q{("[#{PUBIDCHAR}']*"|'[#{PUBIDCHAR}]*')} - EXTERNALID = "(?:(?:(SYSTEM)\\s+#{SYSTEMLITERAL})|(?:(PUBLIC)\\s+#{PUBIDLITERAL}\\s+#{SYSTEMLITERAL}))" - NDATADECL = "\\s+NDATA\\s+#{NAME}" - PEREFERENCE = "%#{NAME};" - ENTITYVALUE = %Q{((?:"(?:[^%&"]|#{PEREFERENCE}|#{REFERENCE})*")|(?:'([^%&']|#{PEREFERENCE}|#{REFERENCE})*'))} - PEDEF = "(?:#{ENTITYVALUE}|#{EXTERNALID})" - ENTITYDEF = "(?:#{ENTITYVALUE}|(?:#{EXTERNALID}(#{NDATADECL})?))" - PEDECL = "<!ENTITY\\s+(%)\\s+#{NAME}\\s+#{PEDEF}\\s*>" - GEDECL = "<!ENTITY\\s+#{NAME}\\s+#{ENTITYDEF}\\s*>" - ENTITYDECL = /\s*(?:#{GEDECL})|(?:#{PEDECL})/um + # Entity constants + PUBIDCHAR = "\x20\x0D\x0Aa-zA-Z0-9\\-()+,./:=?;!*@$_%#" + SYSTEMLITERAL = %Q{((?:"[^"]*")|(?:'[^']*'))} + PUBIDLITERAL = %Q{("[#{PUBIDCHAR}']*"|'[#{PUBIDCHAR}]*')} + EXTERNALID = "(?:(?:(SYSTEM)\\s+#{SYSTEMLITERAL})|(?:(PUBLIC)\\s+#{PUBIDLITERAL}\\s+#{SYSTEMLITERAL}))" + NDATADECL = "\\s+NDATA\\s+#{NAME}" + PEREFERENCE = "%#{NAME};" + ENTITYVALUE = %Q{((?:"(?:[^%&"]|#{PEREFERENCE}|#{REFERENCE})*")|(?:'([^%&']|#{PEREFERENCE}|#{REFERENCE})*'))} + PEDEF = "(?:#{ENTITYVALUE}|#{EXTERNALID})" + ENTITYDEF = "(?:#{ENTITYVALUE}|(?:#{EXTERNALID}(#{NDATADECL})?))" + PEDECL = "<!ENTITY\\s+(%)\\s+#{NAME}\\s+#{PEDEF}\\s*>" + GEDECL = "<!ENTITY\\s+#{NAME}\\s+#{ENTITYDEF}\\s*>" + ENTITYDECL = /\s*(?:#{GEDECL})|(?:#{PEDECL})/um - EREFERENCE = /&(?!#{NAME};)/ + EREFERENCE = /&(?!#{NAME};)/ - DEFAULT_ENTITIES = { - 'gt' => [/>/, '>', '>', />/], - 'lt' => [/</, '<', '<', /</], - 'quot' => [/"/, '"', '"', /"/], - "apos" => [/'/, "'", "'", /'/] - } + DEFAULT_ENTITIES = { + 'gt' => [/>/, '>', '>', />/], + 'lt' => [/</, '<', '<', /</], + 'quot' => [/"/, '"', '"', /"/], + "apos" => [/'/, "'", "'", /'/] + } - def initialize( source ) - self.stream = source - end + def initialize( source ) + self.stream = source + end def add_listener( listener ) if !defined?(@listeners) or !@listeners @@ -119,315 +119,320 @@ module REXML attr_reader :source - def stream=( source ) - if source.kind_of? String - @source = Source.new(source) - elsif source.kind_of? IO - @source = IOSource.new(source) - elsif source.kind_of? Source - @source = source - elsif defined? StringIO and source.kind_of? StringIO - @source = IOSource.new(source) - else - raise "#{source.class} is not a valid input stream. It must be \n"+ - "either a String, IO, StringIO or Source." - end - @closed = nil - @document_status = nil - @tags = [] - @stack = [] - @entities = [] - end + def stream=( source ) + @source = SourceFactory.create_from( source ) + @closed = nil + @document_status = nil + @tags = [] + @stack = [] + @entities = [] + end + + def position + if @source.respond_to? :position + @source.position + else + # FIXME + 0 + end + end - # Returns true if there are no more events - def empty? - #puts "@source.empty? = #{@source.empty?}" - #puts "@stack.empty? = #{@stack.empty?}" + # Returns true if there are no more events + def empty? + #STDERR.puts "@source.empty? = #{@source.empty?}" + #STDERR.puts "@stack.empty? = #{@stack.empty?}" return (@source.empty? and @stack.empty?) - end + end - # Returns true if there are more events. Synonymous with !empty? - def has_next? + # Returns true if there are more events. Synonymous with !empty? + def has_next? return !(@source.empty? and @stack.empty?) - end + end - # Push an event back on the head of the stream. This method - # has (theoretically) infinite depth. - def unshift token - @stack.unshift(token) - end + # Push an event back on the head of the stream. This method + # has (theoretically) infinite depth. + def unshift token + @stack.unshift(token) + end - # Peek at the +depth+ event in the stack. The first element on the stack - # is at depth 0. If +depth+ is -1, will parse to the end of the input - # stream and return the last event, which is always :end_document. - # Be aware that this causes the stream to be parsed up to the +depth+ - # event, so you can effectively pre-parse the entire document (pull the - # entire thing into memory) using this method. - def peek depth=0 - raise %Q[Illegal argument "#{depth}"] if depth < -1 - temp = [] - if depth == -1 - temp.push(pull()) until empty? - else - while @stack.size+temp.size < depth+1 - temp.push(pull()) - end - end - @stack += temp if temp.size > 0 - @stack[depth] - end + # Peek at the +depth+ event in the stack. The first element on the stack + # is at depth 0. If +depth+ is -1, will parse to the end of the input + # stream and return the last event, which is always :end_document. + # Be aware that this causes the stream to be parsed up to the +depth+ + # event, so you can effectively pre-parse the entire document (pull the + # entire thing into memory) using this method. + def peek depth=0 + raise %Q[Illegal argument "#{depth}"] if depth < -1 + temp = [] + if depth == -1 + temp.push(pull()) until empty? + else + while @stack.size+temp.size < depth+1 + temp.push(pull()) + end + end + @stack += temp if temp.size > 0 + @stack[depth] + end - # Returns the next event. This is a +PullEvent+ object. - def pull - if @closed - x, @closed = @closed, nil - return [ :end_element, x ] - end - return [ :end_document ] if empty? - return @stack.shift if @stack.size > 0 - @source.read if @source.buffer.size<2 - if @document_status == nil - @source.consume( /^\s*/um ) - word = @source.match( /(<[^>]*)>/um ) - word = word[1] unless word.nil? - case word - when COMMENT_START - return [ :comment, @source.match( COMMENT_PATTERN, true )[1] ] - when XMLDECL_START - results = @source.match( XMLDECL_PATTERN, true )[1] - version = VERSION.match( results ) - version = version[1] unless version.nil? - encoding = ENCODING.match(results) - encoding = encoding[1] unless encoding.nil? - @source.encoding = encoding - standalone = STANDALONE.match(results) - standalone = standalone[1] unless standalone.nil? - return [ :xmldecl, version, encoding, standalone] - when INSTRUCTION_START - return [ :processing_instruction, *@source.match(INSTRUCTION_PATTERN, true)[1,2] ] - when DOCTYPE_START - md = @source.match( DOCTYPE_PATTERN, true ) - identity = md[1] - close = md[2] - identity =~ IDENTITY - name = $1 - raise REXML::ParseException("DOCTYPE is missing a name") if name.nil? - pub_sys = $2.nil? ? nil : $2.strip - long_name = $3.nil? ? nil : $3.strip - uri = $4.nil? ? nil : $4.strip - args = [ :start_doctype, name, pub_sys, long_name, uri ] - if close == ">" - @document_status = :after_doctype - @source.read if @source.buffer.size<2 - md = @source.match(/^\s*/um, true) - @stack << [ :end_doctype ] - else - @document_status = :in_doctype - end - return args - else - @document_status = :after_doctype - @source.read if @source.buffer.size<2 - md = @source.match(/\s*/um, true) - end - end - if @document_status == :in_doctype - md = @source.match(/\s*(.*?>)/um) - case md[1] - when SYSTEMENTITY - match = @source.match( SYSTEMENTITY, true )[1] - return [ :externalentity, match ] + # Returns the next event. This is a +PullEvent+ object. + def pull + if @closed + x, @closed = @closed, nil + return [ :end_element, x ] + end + return [ :end_document ] if empty? + return @stack.shift if @stack.size > 0 + @source.read if @source.buffer.size<2 + #STDERR.puts "BUFFER = #{@source.buffer.inspect}" + if @document_status == nil + #@source.consume( /^\s*/um ) + word = @source.match( /^((?:\s+)|(?:<[^>]*>))/um ) + word = word[1] unless word.nil? + #STDERR.puts "WORD = #{word.inspect}" + case word + when COMMENT_START + return [ :comment, @source.match( COMMENT_PATTERN, true )[1] ] + when XMLDECL_START + #STDERR.puts "XMLDECL" + results = @source.match( XMLDECL_PATTERN, true )[1] + version = VERSION.match( results ) + version = version[1] unless version.nil? + encoding = ENCODING.match(results) + encoding = encoding[1] unless encoding.nil? + @source.encoding = encoding + standalone = STANDALONE.match(results) + standalone = standalone[1] unless standalone.nil? + return [ :xmldecl, version, encoding, standalone ] + when INSTRUCTION_START + return [ :processing_instruction, *@source.match(INSTRUCTION_PATTERN, true)[1,2] ] + when DOCTYPE_START + md = @source.match( DOCTYPE_PATTERN, true ) + identity = md[1] + close = md[2] + identity =~ IDENTITY + name = $1 + raise REXML::ParseException("DOCTYPE is missing a name") if name.nil? + pub_sys = $2.nil? ? nil : $2.strip + long_name = $3.nil? ? nil : $3.strip + uri = $4.nil? ? nil : $4.strip + args = [ :start_doctype, name, pub_sys, long_name, uri ] + if close == ">" + @document_status = :after_doctype + @source.read if @source.buffer.size<2 + md = @source.match(/^\s*/um, true) + @stack << [ :end_doctype ] + else + @document_status = :in_doctype + end + return args + when /^\s+/ + else + @document_status = :after_doctype + @source.read if @source.buffer.size<2 + md = @source.match(/\s*/um, true) + end + end + if @document_status == :in_doctype + md = @source.match(/\s*(.*?>)/um) + case md[1] + when SYSTEMENTITY + match = @source.match( SYSTEMENTITY, true )[1] + return [ :externalentity, match ] - when ELEMENTDECL_START - return [ :elementdecl, @source.match( ELEMENTDECL_PATTERN, true )[1] ] + when ELEMENTDECL_START + return [ :elementdecl, @source.match( ELEMENTDECL_PATTERN, true )[1] ] - when ENTITY_START - match = @source.match( ENTITYDECL, true ).to_a.compact - match[0] = :entitydecl - 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 is [ :entity, name, PUBLIC, pubid, href ] - else - match[2] = match[2][1..-2] - match.pop if match.size == 4 - # match is [ :entity, name, value ] - end - match << '%' if ref - return match - when ATTLISTDECL_START - md = @source.match( ATTLISTDECL_PATTERN, true ) - raise REXML::ParseException.new( "Bad ATTLIST declaration!", @source ) if md.nil? - element = md[1] - contents = md[0] + when ENTITY_START + match = @source.match( ENTITYDECL, true ).to_a.compact + match[0] = :entitydecl + 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 is [ :entity, name, PUBLIC, pubid, href ] + else + match[2] = match[2][1..-2] + match.pop if match.size == 4 + # match is [ :entity, name, value ] + end + match << '%' if ref + return match + when ATTLISTDECL_START + 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 - end - end - return [ :attlistdecl, element, pairs, contents ] - when NOTATIONDECL_START - md = nil - if @source.match( PUBLIC ) - md = @source.match( PUBLIC, true ) - elsif @source.match( SYSTEM ) - md = @source.match( SYSTEM, true ) - else - raise REXML::ParseException.new( "error parsing notation: no matching pattern", @source ) - end - return [ :notationdecl, md[1], md[2], md[3] ] - when CDATA_END - @document_status = :after_doctype - @source.match( CDATA_END, true ) - return [ :end_doctype ] - end - end - begin - if @source.buffer[0] == ?< - if @source.buffer[1] == ?/ - last_tag = @tags.pop - #md = @source.match_to_consume( '>', CLOSE_MATCH) - md = @source.match( CLOSE_MATCH, true ) - raise REXML::ParseException.new( "Missing end tag for "+ + 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 + end + end + return [ :attlistdecl, element, pairs, contents ] + when NOTATIONDECL_START + md = nil + if @source.match( PUBLIC ) + md = @source.match( PUBLIC, true ) + vals = [md[1],md[2],md[4],md[6]] + elsif @source.match( SYSTEM ) + md = @source.match( SYSTEM, true ) + vals = [md[1],md[2],nil,md[4]] + else + raise REXML::ParseException.new( "error parsing notation: no matching pattern", @source ) + end + return [ :notationdecl, *vals ] + when CDATA_END + @document_status = :after_doctype + @source.match( CDATA_END, true ) + return [ :end_doctype ] + end + end + begin + if @source.buffer[0] == ?< + if @source.buffer[1] == ?/ + last_tag = @tags.pop + #md = @source.match_to_consume( '>', CLOSE_MATCH) + md = @source.match( CLOSE_MATCH, true ) + raise REXML::ParseException.new( "Missing end tag for "+ "'#{last_tag}' (got \"#{md[1]}\")", @source) unless last_tag == md[1] - return [ :end_element, last_tag ] - elsif @source.buffer[1] == ?! - md = @source.match(/\A(\s*[^>]*>)/um) - #puts "SOURCE BUFFER = #{source.buffer}, #{source.buffer.size}" - raise REXML::ParseException.new("Malformed node", @source) unless md - if md[0][2] == ?- - md = @source.match( COMMENT_PATTERN, true ) - return [ :comment, md[1] ] if md - else - md = @source.match( CDATA_PATTERN, true ) - return [ :cdata, md[1] ] if md - end - raise REXML::ParseException.new( "Declarations can only occur "+ - "in the doctype declaration.", @source) - elsif @source.buffer[1] == ?? - md = @source.match( INSTRUCTION_PATTERN, true ) - return [ :processing_instruction, md[1], md[2] ] if md - raise REXML::ParseException.new( "Bad instruction declaration", - @source) - else - # Get the next tag - md = @source.match(TAG_MATCH, true) - raise REXML::ParseException.new("malformed XML: missing tag start", @source) unless md - attrs = [] - if md[2].size > 0 - attrs = md[2].scan( ATTRIBUTE_PATTERN ) - raise REXML::ParseException.new( "error parsing attributes: [#{attrs.join ', '}], excess = \"#$'\"", @source) if $' and $'.strip.size > 0 - end - - if md[4] - @closed = md[1] - else - @tags.push( md[1] ) - end - attributes = {} - attrs.each { |a,b,c| attributes[a] = c } - return [ :start_element, md[1], attributes ] - end - else - md = @source.match( TEXT_PATTERN, true ) + return [ :end_element, last_tag ] + elsif @source.buffer[1] == ?! + md = @source.match(/\A(\s*[^>]*>)/um) + #STDERR.puts "SOURCE BUFFER = #{source.buffer}, #{source.buffer.size}" + raise REXML::ParseException.new("Malformed node", @source) unless md + if md[0][2] == ?- + md = @source.match( COMMENT_PATTERN, true ) + return [ :comment, md[1] ] if md + else + md = @source.match( CDATA_PATTERN, true ) + return [ :cdata, md[1] ] if md + end + raise REXML::ParseException.new( "Declarations can only occur "+ + "in the doctype declaration.", @source) + elsif @source.buffer[1] == ?? + md = @source.match( INSTRUCTION_PATTERN, true ) + return [ :processing_instruction, md[1], md[2] ] if md + raise REXML::ParseException.new( "Bad instruction declaration", + @source) + else + # Get the next tag + md = @source.match(TAG_MATCH, true) + raise REXML::ParseException.new("malformed XML: missing tag start", @source) unless md + attrs = [] + if md[2].size > 0 + attrs = md[2].scan( ATTRIBUTE_PATTERN ) + raise REXML::ParseException.new( "error parsing attributes: [#{attrs.join ', '}], excess = \"#$'\"", @source) if $' and $'.strip.size > 0 + end + + if md[4] + @closed = md[1] + else + @tags.push( md[1] ) + end + attributes = {} + attrs.each { |a,b,c| attributes[a] = c } + return [ :start_element, md[1], attributes ] + end + else + md = @source.match( TEXT_PATTERN, true ) if md[0].length == 0 - #puts "EMPTY = #{empty?}" - #puts "BUFFER = \"#{@source.buffer}\"" + puts "EMPTY = #{empty?}" + puts "BUFFER = \"#{@source.buffer}\"" @source.match( /(\s+)/, true ) end + #STDERR.puts "GOT #{md[1].inspect}" unless md[0].length == 0 #return [ :text, "" ] if md[0].length == 0 - # unnormalized = Text::unnormalize( md[1], self ) - # return PullEvent.new( :text, md[1], unnormalized ) - return [ :text, md[1] ] - end - rescue REXML::ParseException - raise - rescue Exception, NameError => error - raise REXML::ParseException.new( "Exception parsing", - @source, self, (error ? error : $!) ) - end - return [ :dummy ] - end + # unnormalized = Text::unnormalize( md[1], self ) + # return PullEvent.new( :text, md[1], unnormalized ) + return [ :text, md[1] ] + end + rescue REXML::ParseException + raise + rescue Exception, NameError => error + raise REXML::ParseException.new( "Exception parsing", + @source, self, (error ? error : $!) ) + end + return [ :dummy ] + end - def entity( reference, entities ) - value = nil - value = entities[ reference ] if entities - if not value - value = DEFAULT_ENTITIES[ reference ] - value = value[2] if value - end - unnormalize( value, entities ) if value - end + def entity( reference, entities ) + value = nil + value = entities[ reference ] if entities + if not value + value = DEFAULT_ENTITIES[ reference ] + value = value[2] if value + end + unnormalize( value, entities ) if value + end - # Escapes all possible entities - def normalize( input, entities=nil, entity_filter=nil ) - copy = input.clone - # Doing it like this rather than in a loop improves the speed - copy.gsub!( EREFERENCE, '&' ) - entities.each do |key, value| - copy.gsub!( value, "&#{key};" ) unless entity_filter and - entity_filter.include?(entity) - end if entities - copy.gsub!( EREFERENCE, '&' ) - DEFAULT_ENTITIES.each do |key, value| - copy.gsub!( value[3], value[1] ) - end - copy - end + # Escapes all possible entities + def normalize( input, entities=nil, entity_filter=nil ) + copy = input.clone + # Doing it like this rather than in a loop improves the speed + copy.gsub!( EREFERENCE, '&' ) + entities.each do |key, value| + copy.gsub!( value, "&#{key};" ) unless entity_filter and + entity_filter.include?(entity) + end if entities + copy.gsub!( EREFERENCE, '&' ) + DEFAULT_ENTITIES.each do |key, value| + copy.gsub!( value[3], value[1] ) + end + copy + end - # Unescapes all possible entities - def unnormalize( string, entities=nil, filter=nil ) - rv = string.clone - rv.gsub!( /\r\n?/, "\n" ) - matches = rv.scan( REFERENCE_RE ) - return rv if matches.size == 0 - rv.gsub!( /�*((?:\d+)|(?:x[a-fA-F0-9]+));/ ) {|m| - m=$1 - m = "0#{m}" if m[0] == ?x - [Integer(m)].pack('U*') - } - matches.collect!{|x|x[0]}.compact! - if matches.size > 0 - matches.each do |entity_reference| - unless filter and filter.include?(entity_reference) - entity_value = entity( entity_reference, entities ) - if entity_value - re = /&#{entity_reference};/ - rv.gsub!( re, entity_value ) - end - end - end - matches.each do |entity_reference| - unless filter and filter.include?(entity_reference) - er = DEFAULT_ENTITIES[entity_reference] - rv.gsub!( er[0], er[2] ) if er - end - end - rv.gsub!( /&/, '&' ) - end - rv - end - end - end + # Unescapes all possible entities + def unnormalize( string, entities=nil, filter=nil ) + rv = string.clone + rv.gsub!( /\r\n?/, "\n" ) + matches = rv.scan( REFERENCE_RE ) + return rv if matches.size == 0 + rv.gsub!( /�*((?:\d+)|(?:x[a-fA-F0-9]+));/ ) {|m| + m=$1 + m = "0#{m}" if m[0] == ?x + [Integer(m)].pack('U*') + } + matches.collect!{|x|x[0]}.compact! + if matches.size > 0 + matches.each do |entity_reference| + unless filter and filter.include?(entity_reference) + entity_value = entity( entity_reference, entities ) + if entity_value + re = /&#{entity_reference};/ + rv.gsub!( re, entity_value ) + end + end + end + matches.each do |entity_reference| + unless filter and filter.include?(entity_reference) + er = DEFAULT_ENTITIES[entity_reference] + rv.gsub!( er[0], er[2] ) if er + end + end + rv.gsub!( /&/, '&' ) + end + rv + end + end + end end =begin diff --git a/lib/rexml/parsers/pullparser.rb b/lib/rexml/parsers/pullparser.rb index 0a328ea8fc..36dc7160c3 100644 --- a/lib/rexml/parsers/pullparser.rb +++ b/lib/rexml/parsers/pullparser.rb @@ -1,95 +1,99 @@ +require 'forwardable' + require 'rexml/parseexception' require 'rexml/parsers/baseparser' require 'rexml/xmltokens' module REXML - module Parsers - # = Using the Pull Parser - # <em>This API is experimental, and subject to change.</em> - # parser = PullParser.new( "<a>text<b att='val'/>txet</a>" ) - # while parser.has_next? - # res = parser.next - # puts res[1]['att'] if res.start_tag? and res[0] == 'b' - # end - # See the PullEvent class for information on the content of the results. - # The data is identical to the arguments passed for the various events to - # the StreamListener API. - # - # Notice that: - # parser = PullParser.new( "<a>BAD DOCUMENT" ) - # while parser.has_next? - # res = parser.next - # raise res[1] if res.error? - # end - # - # Nat Price gave me some good ideas for the API. - class PullParser - include XMLTokens - - def initialize stream - @entities = {} + module Parsers + # = Using the Pull Parser + # <em>This API is experimental, and subject to change.</em> + # parser = PullParser.new( "<a>text<b att='val'/>txet</a>" ) + # while parser.has_next? + # res = parser.next + # puts res[1]['att'] if res.start_tag? and res[0] == 'b' + # end + # See the PullEvent class for information on the content of the results. + # The data is identical to the arguments passed for the various events to + # the StreamListener API. + # + # Notice that: + # parser = PullParser.new( "<a>BAD DOCUMENT" ) + # while parser.has_next? + # res = parser.next + # raise res[1] if res.error? + # end + # + # Nat Price gave me some good ideas for the API. + class PullParser + include XMLTokens + extend Forwardable + + def_delegators( :@parser, :has_next? ) + def_delegators( :@parser, :entity ) + def_delegators( :@parser, :empty? ) + def_delegators( :@parser, :source ) + + def initialize stream + @entities = {} @listeners = nil @parser = BaseParser.new( stream ) - end + @my_stack = [] + end def add_listener( listener ) @listeners = [] unless @listeners @listeners << listener end - def each - while has_next? - yield self.pull - end - end - - def peek depth=0 - PullEvent.new(@parser.peek(depth)) - end - - def has_next? - @parser.has_next? + def each + while has_next? + yield self.pull + end end - def pull - event = @parser.pull - case event[0] - when :entitydecl - @entities[ event[1] ] = - event[2] unless event[2] =~ /PUBLIC|SYSTEM/ - when :text - unnormalized = @parser.unnormalize( event[1], @entities ) - event << unnormalized - end - PullEvent.new( event ) - end - - def unshift token - @parser.unshift token + def peek depth=0 + if @my_stack.length <= depth + (depth - @my_stack.length + 1).times { + e = PullEvent.new(@parser.pull) + @my_stack.push(e) + } + end + @my_stack[depth] end - def entity reference - @parser.entity( reference ) + def pull + return @my_stack.shift if @my_stack.length > 0 + + event = @parser.pull + case event[0] + when :entitydecl + @entities[ event[1] ] = + event[2] unless event[2] =~ /PUBLIC|SYSTEM/ + when :text + unnormalized = @parser.unnormalize( event[1], @entities ) + event << unnormalized + end + PullEvent.new( event ) end - def empty? - @parser.empty? + def unshift token + @my_stack.unshift token + end + end + + # A parsing event. The contents of the event are accessed as an +Array?, + # and the type is given either by the ...? methods, or by accessing the + # +type+ accessor. The contents of this object vary from event to event, + # but are identical to the arguments passed to +StreamListener+s for each + # event. + class PullEvent + # The type of this event. Will be one of :tag_start, :tag_end, :text, + # :processing_instruction, :comment, :doctype, :attlistdecl, :entitydecl, + # :notationdecl, :entity, :cdata, :xmldecl, or :error. + def initialize(arg) + @contents = arg end - - end - - # A parsing event. The contents of the event are accessed as an +Array?, - # and the type is given either by the ...? methods, or by accessing the - # +type+ accessor. The contents of this object vary from event to event, - # but are identical to the arguments passed to +StreamListener+s for each - # event. - class PullEvent - # The type of this event. Will be one of :tag_start, :tag_end, :text, - # :processing_instruction, :comment, :doctype, :attlistdecl, :entitydecl, - # :notationdecl, :entity, :cdata, :xmldecl, or :error. - def initialize(arg) - @contents = arg - end def []( start, endd=nil) if start.kind_of? Range @@ -103,90 +107,90 @@ module REXML else raise "Illegal argument #{start.inspect} (#{start.class})" end - end - - def event_type - @contents[0] - end - - # Content: [ String tag_name, Hash attributes ] - def start_element? - @contents[0] == :start_element - end - - # Content: [ String tag_name ] - def end_element? - @contents[0] == :end_element - end - - # Content: [ String raw_text, String unnormalized_text ] - def text? - @contents[0] == :text - end - - # Content: [ String text ] - def instruction? - @contents[0] == :processing_instruction - end - - # Content: [ String text ] - def comment? - @contents[0] == :comment - end - - # Content: [ String name, String pub_sys, String long_name, String uri ] - def doctype? - @contents[0] == :start_doctype - end - - # Content: [ String text ] - def attlistdecl? - @contents[0] == :attlistdecl - end - - # Content: [ String text ] - def elementdecl? - @contents[0] == :elementdecl - end - - # Due to the wonders of DTDs, an entity declaration can be just about - # anything. There's no way to normalize it; you'll have to interpret the - # content yourself. However, the following is true: - # - # * If the entity declaration is an internal entity: - # [ String name, String value ] - # Content: [ String text ] - def entitydecl? - @contents[0] == :entitydecl - end - - # Content: [ String text ] - def notationdecl? - @contents[0] == :notationdecl - end - - # Content: [ String text ] - def entity? - @contents[0] == :entity - end - - # Content: [ String text ] - def cdata? - @contents[0] == :cdata - end - - # Content: [ String version, String encoding, String standalone ] - def xmldecl? - @contents[0] == :xmldecl - end - - def error? - @contents[0] == :error - end - - def inspect + end + + def event_type + @contents[0] + end + + # Content: [ String tag_name, Hash attributes ] + def start_element? + @contents[0] == :start_element + end + + # Content: [ String tag_name ] + def end_element? + @contents[0] == :end_element + end + + # Content: [ String raw_text, String unnormalized_text ] + def text? + @contents[0] == :text + end + + # Content: [ String text ] + def instruction? + @contents[0] == :processing_instruction + end + + # Content: [ String text ] + def comment? + @contents[0] == :comment + end + + # Content: [ String name, String pub_sys, String long_name, String uri ] + def doctype? + @contents[0] == :start_doctype + end + + # Content: [ String text ] + def attlistdecl? + @contents[0] == :attlistdecl + end + + # Content: [ String text ] + def elementdecl? + @contents[0] == :elementdecl + end + + # Due to the wonders of DTDs, an entity declaration can be just about + # anything. There's no way to normalize it; you'll have to interpret the + # content yourself. However, the following is true: + # + # * If the entity declaration is an internal entity: + # [ String name, String value ] + # Content: [ String text ] + def entitydecl? + @contents[0] == :entitydecl + end + + # Content: [ String text ] + def notationdecl? + @contents[0] == :notationdecl + end + + # Content: [ String text ] + def entity? + @contents[0] == :entity + end + + # Content: [ String text ] + def cdata? + @contents[0] == :cdata + end + + # Content: [ String version, String encoding, String standalone ] + def xmldecl? + @contents[0] == :xmldecl + end + + def error? + @contents[0] == :error + end + + def inspect @contents[0].to_s + ": " + @contents[1..-1].inspect - end - end - end + end + end + end end diff --git a/lib/rexml/parsers/sax2parser.rb b/lib/rexml/parsers/sax2parser.rb index d5ee1bcfcd..61a216cec1 100644 --- a/lib/rexml/parsers/sax2parser.rb +++ b/lib/rexml/parsers/sax2parser.rb @@ -1,9 +1,11 @@ require 'rexml/parsers/baseparser' require 'rexml/parseexception' require 'rexml/namespace' +require 'rexml/text' module REXML module Parsers + # SAX2Parser class SAX2Parser def initialize source @parser = BaseParser.new(source) @@ -36,6 +38,10 @@ module REXML # :start_prefix_mapping, :end_prefix_mapping, :characters, # :processing_instruction, :doctype, :attlistdecl, :elementdecl, # :entitydecl, :notationdecl, :cdata, :xmldecl, :comment + # + # There is an additional symbol that can be listened for: :progress. + # This will be called for every event generated, passing in the current + # stream position. # # Array contains regular expressions or strings which will be matched # against fully qualified element names. @@ -161,6 +167,7 @@ module REXML :elementdecl, :cdata, :notationdecl, :xmldecl handle( *event ) end + handle( :progress, @parser.position ) end end diff --git a/lib/rexml/parsers/streamparser.rb b/lib/rexml/parsers/streamparser.rb index 996d613e15..256d0f611c 100644 --- a/lib/rexml/parsers/streamparser.rb +++ b/lib/rexml/parsers/streamparser.rb @@ -1,42 +1,46 @@ module REXML - module Parsers - class StreamParser - def initialize source, listener - @listener = listener - @parser = BaseParser.new( source ) - end - + module Parsers + class StreamParser + def initialize source, listener + @listener = listener + @parser = BaseParser.new( source ) + end + def add_listener( listener ) @parser.add_listener( listener ) end - - def parse - # entity string - while true - event = @parser.pull - case event[0] - when :end_document - return - when :start_element - attrs = event[2].each do |n, v| - event[2][n] = @parser.unnormalize( v ) - end - @listener.tag_start( event[1], attrs ) - when :end_element - @listener.tag_end( event[1] ) - when :text - normalized = @parser.unnormalize( event[1] ) - @listener.text( normalized ) - when :processing_instruction - @listener.instruction( *event[1,2] ) + + def parse + # entity string + while true + event = @parser.pull + case event[0] + when :end_document + return + when :start_element + attrs = event[2].each do |n, v| + event[2][n] = @parser.unnormalize( v ) + end + @listener.tag_start( event[1], attrs ) + when :end_element + @listener.tag_end( event[1] ) + when :text + normalized = @parser.unnormalize( event[1] ) + @listener.text( normalized ) + when :processing_instruction + @listener.instruction( *event[1,2] ) when :start_doctype @listener.doctype( *event[1..-1] ) - when :comment, :attlistdecl, :notationdecl, :elementdecl, - :entitydecl, :cdata, :xmldecl, :attlistdecl - @listener.send( event[0].to_s, *event[1..-1] ) - end - end - end - end - end + when :end_doctype + # FIXME: remove this condition for milestone:3.2 + @listener.doctype_end if @listener.respond_to? :doctype_end + when :comment, :attlistdecl, :cdata, :xmldecl, :elementdecl + @listener.send( event[0].to_s, *event[1..-1] ) + when :entitydecl, :notationdecl + @listener.send( event[0].to_s, event[1..-1] ) + end + end + end + end + end end diff --git a/lib/rexml/parsers/treeparser.rb b/lib/rexml/parsers/treeparser.rb index 57d11f7e23..500a53f426 100644 --- a/lib/rexml/parsers/treeparser.rb +++ b/lib/rexml/parsers/treeparser.rb @@ -19,8 +19,12 @@ module REXML begin while true event = @parser.pull + #STDERR.puts "TREEPARSER GOT #{event.inspect}" case event[0] when :end_document + unless tag_stack.empty? + raise ParseException.new("No close tag for #{tag_stack.inspect}") + end return when :start_element tag_stack.push(event[1]) @@ -35,10 +39,10 @@ module REXML @build_context[-1] << event[1] else @build_context.add( - Text.new( event[1], @build_context.whitespace, nil, true ) + Text.new(event[1], @build_context.whitespace, nil, true) ) unless ( - event[1].strip.size==0 and - @build_context.ignore_whitespace_nodes + @build_context.ignore_whitespace_nodes and + event[1].strip.size==0 ) end end |