diff options
| -rw-r--r-- | src/compiler/scala/tools/nsc/ast/parser/MarkupParsers.scala | 15 | ||||
| -rw-r--r-- | src/compiler/scala/tools/nsc/ast/parser/Scanners.scala | 3 | ||||
| -rw-r--r-- | src/dotnet-library/scala/xml/NodeTraverser.scala | 1 | ||||
| -rw-r--r-- | src/dotnet-library/scala/xml/Parsing.scala | 1 | ||||
| -rw-r--r-- | src/library/scala/xml/MetaData.scala | 22 | ||||
| -rw-r--r-- | src/library/scala/xml/NodeTraverser.scala | 37 | ||||
| -rw-r--r-- | src/library/scala/xml/Null.scala | 17 | ||||
| -rw-r--r-- | src/library/scala/xml/Parsing.scala | 97 | ||||
| -rw-r--r-- | src/library/scala/xml/PrettyPrinter.scala | 32 | ||||
| -rw-r--r-- | src/library/scala/xml/include/sax/Main.scala | 140 | ||||
| -rw-r--r-- | src/library/scala/xml/include/sax/XIncludeFilter.scala | 23 | ||||
| -rw-r--r-- | src/library/scala/xml/parsing/ConstructingParser.scala | 15 | ||||
| -rw-r--r-- | src/library/scala/xml/parsing/MarkupParser.scala | 100 | ||||
| -rw-r--r-- | src/library/scala/xml/parsing/XhtmlParser.scala | 41 | ||||
| -rw-r--r-- | src/library/scala/xml/pull/XMLEventReader.scala | 2 | ||||
| -rw-r--r-- | test/files/jvm/unittest_xml.scala | 17 |
16 files changed, 133 insertions, 430 deletions
diff --git a/src/compiler/scala/tools/nsc/ast/parser/MarkupParsers.scala b/src/compiler/scala/tools/nsc/ast/parser/MarkupParsers.scala index 030b2a4732..1e254f7e51 100644 --- a/src/compiler/scala/tools/nsc/ast/parser/MarkupParsers.scala +++ b/src/compiler/scala/tools/nsc/ast/parser/MarkupParsers.scala @@ -11,8 +11,9 @@ import scala.collection.mutable import mutable.{ Buffer, ArrayBuffer, ListBuffer, HashMap } import scala.util.control.ControlException import scala.tools.nsc.util.{Position,NoPosition,SourceFile,CharArrayReader} -import scala.xml.{Text, TextBuffer} -import SourceFile.{SU,LF} +import scala.xml.{ Text, TextBuffer } +import scala.xml.Utility.{ isNameStart, isNameChar, isSpace } +import SourceFile.{ SU, LF } import scala.annotation.switch // XXX/Note: many/most of the functions in here are almost direct cut and pastes @@ -117,7 +118,7 @@ trait MarkupParsers def xAttributes = { val aMap = new HashMap[String, Tree]() - while (xml.Parsing.isNameStart(ch)) { + while (isNameStart(ch)) { val start = curOffset val key = xName xEQ @@ -405,13 +406,13 @@ trait MarkupParsers */ def xName: String = { if (ch == SU) throw TruncatedXML - else if (!xml.Parsing.isNameStart(ch)) + else if (!isNameStart(ch)) return errorAndResult("name expected, but char '%s' cannot start a name" format ch, "") val buf = new StringBuilder do buf append nextch - while (xml.Parsing.isNameChar(ch)) + while (isNameChar(ch)) if (buf.last == ':') { reportSyntaxError( "name cannot end in ':'" ) @@ -424,11 +425,11 @@ trait MarkupParsers def xEQ = { xSpaceOpt; xToken('='); xSpaceOpt } /** skip optional space S? */ - def xSpaceOpt = { while (xml.Parsing.isSpace(ch)) { nextch }} + def xSpaceOpt = { while (isSpace(ch)) { nextch }} /** scan [3] S ::= (#x20 | #x9 | #xD | #xA)+ */ def xSpace = - if (xml.Parsing.isSpace(ch)) { nextch; xSpaceOpt } + if (isSpace(ch)) { nextch; xSpaceOpt } else if (ch == SU) throw TruncatedXML else reportSyntaxError("whitespace expected") diff --git a/src/compiler/scala/tools/nsc/ast/parser/Scanners.scala b/src/compiler/scala/tools/nsc/ast/parser/Scanners.scala index 345edb505e..01a7f31462 100644 --- a/src/compiler/scala/tools/nsc/ast/parser/Scanners.scala +++ b/src/compiler/scala/tools/nsc/ast/parser/Scanners.scala @@ -11,6 +11,7 @@ import SourceFile.{LF, FF, CR, SU} import Tokens._ import scala.annotation.switch import scala.collection.mutable.{ListBuffer, ArrayBuffer} +import scala.xml.Utility.{ isNameStart } trait Scanners { val global : Global @@ -264,7 +265,7 @@ trait Scanners { val last = if (charOffset >= 2) buf(charOffset - 2) else ' ' nextChar() last match { - case ' '|'\t'|'\n'|'{'|'('|'>' if xml.Parsing.isNameStart(ch) || ch == '!' || ch == '?' => + case ' '|'\t'|'\n'|'{'|'('|'>' if isNameStart(ch) || ch == '!' || ch == '?' => token = XMLSTART case _ => // Console.println("found '<', but last is '"+in.last+"'"); // DEBUG diff --git a/src/dotnet-library/scala/xml/NodeTraverser.scala b/src/dotnet-library/scala/xml/NodeTraverser.scala deleted file mode 100644 index 87aca3a120..0000000000 --- a/src/dotnet-library/scala/xml/NodeTraverser.scala +++ /dev/null @@ -1 +0,0 @@ -/* NodeTraverser.scala does not exist for the dotnet target */ diff --git a/src/dotnet-library/scala/xml/Parsing.scala b/src/dotnet-library/scala/xml/Parsing.scala deleted file mode 100644 index 510a535888..0000000000 --- a/src/dotnet-library/scala/xml/Parsing.scala +++ /dev/null @@ -1 +0,0 @@ -/* Parsing.scala does not exist for the dotnet target */ diff --git a/src/library/scala/xml/MetaData.scala b/src/library/scala/xml/MetaData.scala index 280f2b7871..f45da11211 100644 --- a/src/library/scala/xml/MetaData.scala +++ b/src/library/scala/xml/MetaData.scala @@ -139,7 +139,7 @@ abstract class MetaData extends Iterable[MetaData] def isPrefixed: Boolean - /** deep equals method */ + /** deep equals method - XXX */ override def equals(that: Any) = that match { case m: MetaData => (this.length == m.length) && @@ -156,9 +156,9 @@ abstract class MetaData extends Iterable[MetaData] def equals1(that: MetaData): Boolean /** filters this sequence of meta data */ - override def filter(f: MetaData => Boolean): MetaData = { - if (f(this)) copy(next filter f) else next filter f - } + override def filter(f: MetaData => Boolean): MetaData = + if (f(this)) copy(next filter f) + else next filter f /** returns key of this MetaData item */ def key: String @@ -167,7 +167,7 @@ abstract class MetaData extends Iterable[MetaData] def value: Seq[Node] /** maps this sequence of meta data */ - def map(f: MetaData => Text): List[Text] = f(this)::(next map f) + def map(f: MetaData => Text): List[Text] = (iterator map f).toList /** returns Null or the next MetaData item */ def next: MetaData @@ -178,16 +178,12 @@ abstract class MetaData extends Iterable[MetaData] * @param key * @return value in Some(Seq[Node]) if key is found, None otherwise */ - final def get(key: String): Option[Seq[Node]] = apply(key) match { - case null => None - case x => Some(x) - } + final def get(key: String): Option[Seq[Node]] = Option(apply(key)) /** same as get(uri, owner.scope, key) */ final def get(uri: String, owner: Node, key: String): Option[Seq[Node]] = get(uri, owner.scope, key) - /** gets value of qualified (prefixed) attribute with given key. * * @param uri namespace of key @@ -196,10 +192,7 @@ abstract class MetaData extends Iterable[MetaData] * @return value as Some[Seq[Node]] if key is found, None otherwise */ final def get(uri: String, scope: NamespaceBinding, key: String): Option[Seq[Node]] = - apply(uri, scope, key) match { - case null => None - case x => Some(x) - } + Option(apply(uri, scope, key)) override def hashCode(): Int @@ -244,5 +237,4 @@ abstract class MetaData extends Iterable[MetaData] */ final def remove(namespace: String, owner: Node, key: String): MetaData = remove(namespace, owner.scope, key) - } diff --git a/src/library/scala/xml/NodeTraverser.scala b/src/library/scala/xml/NodeTraverser.scala deleted file mode 100644 index cec5341073..0000000000 --- a/src/library/scala/xml/NodeTraverser.scala +++ /dev/null @@ -1,37 +0,0 @@ -/* __ *\ -** ________ ___ / / ___ Scala API ** -** / __/ __// _ | / / / _ | (c) 2003-2009, LAMP/EPFL ** -** __\ \/ /__/ __ |/ /__/ __ | http://scala-lang.org/ ** -** /____/\___/_/ |_/____/_/ | | ** -** |/ ** -\* */ - -// $Id$ - - -package scala.xml - -/** This class ... - * - * @author Burak Emir - * @version 1.0 - */ -abstract class NodeTraverser extends parsing.MarkupHandler { - - def traverse(n: Node): Unit = n match { - case x:ProcInstr => - procInstr(0, x.target, x.text) - case x:Comment => - comment(0, x.text) - case x:Text => - text(0, x.data) - case x:EntityRef => - entityRef(0, x.entityName) - case _ => - elemStart(0, n.prefix, n.label, n.attributes, n.scope) - for (m <- n.child) traverse(m) - elem(0, n.prefix, n.label, n.attributes, n.scope, NodeSeq.fromSeq(n.child)) - elemEnd(0, n.prefix, n.label) - } - -} diff --git a/src/library/scala/xml/Null.scala b/src/library/scala/xml/Null.scala index 7718c61493..9cda330057 100644 --- a/src/library/scala/xml/Null.scala +++ b/src/library/scala/xml/Null.scala @@ -11,6 +11,8 @@ package scala.xml +import Utility.{ isNameStart } + case object Null extends MetaData { /** appends given MetaData items to this MetaData list */ @@ -25,18 +27,19 @@ case object Null extends MetaData { override def filter(f: MetaData => Boolean): MetaData = this - /** returns null */ def getNamespace(owner: Node) = null final override def hasNext = false + def next = null + def key = null + def value = null final override def length = 0 - final override def length(i: Int) = i def isPrefixed = false - /** deep equals method */ + /** deep equals method - XXX */ override def equals(that: Any) = that match { case m: MetaData => m.length == 0 case _ => false @@ -44,17 +47,11 @@ case object Null extends MetaData { def equals1(that:MetaData) = that.length == 0 - def key = null - - def value = null - override def map(f: MetaData => Text): List[Text] = Nil - def next = null - /** null */ def apply(key: String) = { - if(!Parsing.isNameStart (key charAt 0)) + if(!isNameStart(key charAt 0)) throw new IllegalArgumentException("not a valid attribute name '"+key+"', so can never match !") null } diff --git a/src/library/scala/xml/Parsing.scala b/src/library/scala/xml/Parsing.scala deleted file mode 100644 index 3f64ff63e2..0000000000 --- a/src/library/scala/xml/Parsing.scala +++ /dev/null @@ -1,97 +0,0 @@ -/* __ *\ -** ________ ___ / / ___ Scala API ** -** / __/ __// _ | / / / _ | (c) 2003-2009, LAMP/EPFL ** -** __\ \/ /__/ __ |/ /__/ __ | http://scala-lang.org/ ** -** /____/\___/_/ |_/____/_/ | | ** -** |/ ** -\* */ - -// $Id$ - - -package scala.xml - - -/** The object <code>Parsing</code> ... - * - * @author Burak Emir - * @version 1.0 - * - * @deprecated use either <code>parsing.TokenTests</code> or - * <code>Utilty</code> (helper functions for parsing XML fragments). - */ -object Parsing { - - /** <pre>(#x20 | #x9 | #xD | #xA)</pre> */ - final def isSpace(ch: Char): Boolean = ch match { - case '\u0009' | '\u000A' | '\u000D' | '\u0020' => true - case _ => false - } - - /** <pre>(#x20 | #x9 | #xD | #xA)+</pre> */ - final def isSpace(cs: Seq[Char]): Boolean = cs forall isSpace - - /** <pre>NameChar ::= Letter | Digit | '.' | '-' | '_' | ':' - * | CombiningChar | Extender</pre> - * - * see [4] and Appendix B of XML 1.0 specification - */ - private val nameCharTypeList = { - import java.lang.Character._ - List( - COMBINING_SPACING_MARK, // Mc - ENCLOSING_MARK, // Me - NON_SPACING_MARK, // Mn - MODIFIER_LETTER, // Lm - DECIMAL_DIGIT_NUMBER // Nd - ) - } - def isNameChar(ch: Char) = - isNameStart(ch) || List('.', '-', ':').contains(ch) || - nameCharTypeList.contains(Character.getType(ch).asInstanceOf[Byte]) - - /** <pre>NameStart ::= ( Letter | '_' )</pre> - * where Letter means in one of the Unicode general - * categories { Ll, Lu, Lo, Lt, Nl } - * - * We do not allow a name to start with ':'. - * see [3] and Appendix B of XML 1.0 specification - */ - def isNameStart(ch: Char) = - java.lang.Character.getType(ch).asInstanceOf[Byte] match { - case java.lang.Character.LOWERCASE_LETTER => true - case java.lang.Character.UPPERCASE_LETTER => true - case java.lang.Character.OTHER_LETTER => true - case java.lang.Character.TITLECASE_LETTER => true - case java.lang.Character.LETTER_NUMBER => true - case _ => ch == '_' - } - - /** <pre>Name ::= ( Letter | '_' ) (NameChar)*</pre> - * - * see [5] of XML 1.0 specification - */ - def isName(s: String): Boolean = - if (s.length() > 0) { - val z: Seq[Char] = s - val y = z.iterator - if (isNameStart(y.next)) { - while (y.hasNext && isNameChar(y.next)) {} - !y.hasNext - } else false - } else false - - def isPubIDChar(c: Char) = c match { - case '\u0020' | '\u000D' | '\u000A' => true - case _ if - ('0' < c && c < '9')||('a' < c && c < 'z')||('A' < c && c < 'Z') => true - case '-' | '\''| '(' | ')' | '+' | ',' | '.' | '/' | ':' | '=' | - '?' | ';' | '!' | '*' | '#' | '@' | '$' | '_' | '%' => true - case _ => false - } - - def checkSysID(s: String): Boolean = - s.indexOf('"') == -1 || s.indexOf('\'') == -1 - - def checkPubID(s: String): Boolean = s forall isPubIDChar -} diff --git a/src/library/scala/xml/PrettyPrinter.scala b/src/library/scala/xml/PrettyPrinter.scala index 1753860f50..8b2193fba8 100644 --- a/src/library/scala/xml/PrettyPrinter.scala +++ b/src/library/scala/xml/PrettyPrinter.scala @@ -85,6 +85,7 @@ class PrettyPrinter(width: Int, step: Int) { * @return ... */ protected def makeBox(ind: Int, s: String) = { + // XXX um... if (cur < ind) cur == ind if (cur + s.length > width) { // fits in this line @@ -257,14 +258,6 @@ class PrettyPrinter(width: Int, step: Int) { // public convenience methods - /** returns a formatted string containing well-formed XML with - * default namespace prefix mapping - * - * @param n the node to be serialized - * @return ... - */ - def format(n: Node): String = format(n, null) //Utility.defaultPrefixes(n)) - /** Returns a formatted string containing well-formed XML with * given namespace to prefix mapping. * @@ -272,32 +265,23 @@ class PrettyPrinter(width: Int, step: Int) { * @param pmap the namespace to prefix mapping * @return ... */ - def format(n: Node, pscope: NamespaceBinding): String = + def format(n: Node, pscope: NamespaceBinding = null): String = sbToString(format(n, pscope, _)) - /** Returns a formatted string containing well-formed XML nodes with - * default namespace prefix mapping. - * - * @param nodes ... - * @return ... - */ - def formatNodes(nodes: Seq[Node]): String = - formatNodes(nodes, null) - /** Returns a formatted string containing well-formed XML. * - * @param nodes the sequence of nodes to be serialized - * @param pmap the namespace to prefix mapping + * @param nodes the sequence of nodes to be serialized + * @param pscope the namespace to prefix mapping */ - def formatNodes(nodes: Seq[Node], pscope: NamespaceBinding): String = + def formatNodes(nodes: Seq[Node], pscope: NamespaceBinding = null): String = sbToString(formatNodes(nodes, pscope, _)) /** Appends a formatted string containing well-formed XML with * the given namespace to prefix mapping to the given stringbuffer. * - * @param n the node to be serialized - * @param pmap the namespace to prefix mapping - * @param sb the string buffer to which to append to + * @param nodes the nodes to be serialized + * @param pscope the namespace to prefix mapping + * @param sb the string buffer to which to append to */ def formatNodes(nodes: Seq[Node], pscope: NamespaceBinding, sb: StringBuilder): Unit = nodes foreach (n => sb append format(n, pscope)) diff --git a/src/library/scala/xml/include/sax/Main.scala b/src/library/scala/xml/include/sax/Main.scala index 23b379af2b..4df95d1046 100644 --- a/src/library/scala/xml/include/sax/Main.scala +++ b/src/library/scala/xml/include/sax/Main.scala @@ -10,99 +10,73 @@ package scala.xml package include.sax -import scala.xml.include._ -import org.xml.sax.SAXException -import org.xml.sax.SAXParseException -import org.xml.sax.EntityResolver +import scala.xml.include._ +import scala.util.control.Exception.{ catching, ignoring } +import org.xml.sax.{ SAXException, SAXParseException, EntityResolver, XMLReader } import org.xml.sax.helpers.XMLReaderFactory -import org.xml.sax.XMLReader object Main { + private val xercesClass = "org.apache.xerces.parsers.SAXParser" + private val namespacePrefixes = "http://xml.org/sax/features/namespace-prefixes" + private val lexicalHandler = "http://xml.org/sax/properties/lexical-handler" - /** - * The driver method for xinc - * Output is written to System.out via Conolse - * </p> - * - * @param args contains the URLs and/or filenames - * of the documents to be procesed. - */ - def main(args: Array[String]) { - var parser: XMLReader = null - var err = false - try { - parser = XMLReaderFactory.createXMLReader() - } - catch { - case e:SAXException => - try { - parser = XMLReaderFactory.createXMLReader( - "org.apache.xerces.parsers.SAXParser") - } catch { - case e2:SAXException => - System.err.println("Could not find an XML parser") - err = true - } - } + /** + * The driver method for xinc + * Output is written to System.out via Conolse + * </p> + * + * @param args contains the URLs and/or filenames + * of the documents to be procesed. + */ + def main(args: Array[String]) { + def saxe[T](body: => T) = catching[T](classOf[SAXException]) opt body + def error(msg: String) = System.err.println(msg) + + val parser: XMLReader = + saxe[XMLReader](XMLReaderFactory.createXMLReader()) getOrElse ( + saxe[XMLReader](XMLReaderFactory.createXMLReader(xercesClass)) getOrElse ( + return error("Could not find an XML parser") + ) + ) + + // Need better namespace handling + try parser.setFeature(namespacePrefixes, true) + catch { case e: SAXException => return System.err.println(e) } + + if (args.isEmpty) + return - if(err) return; - // Need better namespace handling + val (resolver, args2): (Option[EntityResolver], Array[String]) = + if (args.size < 2 || args(0) != "-r") (None, args) + else catching(classOf[Exception]) opt { + val r = Class.forName(args(1)).newInstance().asInstanceOf[EntityResolver] + parser setEntityResolver r + (r, args drop 2) + } orElse (return error("Could not load requested EntityResolver")) + + for (arg <- args2) { try { - parser.setFeature("http://xml.org/sax/features/namespace-prefixes", true); - } - catch { - case e:SAXException => - System.err.println(e) - err = true - } - if (err) return + val includer = new XIncludeFilter() + includer setParent parser + val s = new XIncluder(System.out, "UTF-8") + includer setContentHandler s - if (args.length == 0) return - var resolver: EntityResolver = null - var arg: Int = 0 - if (args(0).equals("-r")) { - try { - resolver = Class.forName(args(1)).newInstance().asInstanceOf[EntityResolver]; - parser.setEntityResolver(resolver); - } - catch { - case ex:Exception => - System.err.println("Could not load requested EntityResolver") - err = true + resolver map (includer setEntityResolver _) + // SAXException here means will not support comments + ignoring(classOf[SAXException]) { + includer.setProperty(lexicalHandler, s) + s setFilter includer } - arg = 2 + includer parse arg } - if (err) return - - while (arg < args.length) { - try { - val includer = new XIncludeFilter(); - includer.setParent(parser) - val s = new XIncluder(System.out, "UTF-8") - includer.setContentHandler(s) - if (resolver != null) includer.setEntityResolver(resolver) - try { - includer.setProperty( - "http://xml.org/sax/properties/lexical-handler", - s) - s.setFilter(includer) - } - catch { - case e:SAXException => // Will not support comments - } - includer.parse(args(arg)) - } - catch { - case e:SAXParseException => - System.err.println(e) - System.err.println("Problem in " + e.getSystemId() - + " at line " + e.getLineNumber()) - case e: Exception => // be specific about exceptions???? - System.err.println(e) - e.printStackTrace() - } - arg += 1 + catch { + case e: SAXParseException => + error(e.toString) + error("Problem in %s at line %d".format(e.getSystemId, e.getLineNumber)) + case e: SAXException => + error(e.toString) } } + } } diff --git a/src/library/scala/xml/include/sax/XIncludeFilter.scala b/src/library/scala/xml/include/sax/XIncludeFilter.scala index ed8953ea69..222c9f39f8 100644 --- a/src/library/scala/xml/include/sax/XIncludeFilter.scala +++ b/src/library/scala/xml/include/sax/XIncludeFilter.scala @@ -12,24 +12,11 @@ package scala.xml package include.sax import scala.xml.include._ -import org.xml.sax.Attributes -import org.xml.sax.SAXException -import org.xml.sax.XMLReader -import org.xml.sax.EntityResolver -import org.xml.sax.Locator -import org.xml.sax.helpers.XMLReaderFactory -import org.xml.sax.helpers.XMLFilterImpl -import org.xml.sax.helpers.NamespaceSupport -import org.xml.sax.helpers.AttributesImpl - -import java.net.URL -import java.net.URLConnection -import java.net.MalformedURLException -import java.io.UnsupportedEncodingException -import java.io.IOException -import java.io.InputStream -import java.io.BufferedInputStream -import java.io.InputStreamReader +import org.xml.sax.{ Attributes, SAXException, XMLReader, EntityResolver, Locator } +import org.xml.sax.helpers.{ XMLReaderFactory, XMLFilterImpl, NamespaceSupport, AttributesImpl } + +import java.net.{ URL, URLConnection, MalformedURLException } +import java.io.{ UnsupportedEncodingException, IOException, InputStream, BufferedInputStream, InputStreamReader } import java.util.Stack /** diff --git a/src/library/scala/xml/parsing/ConstructingParser.scala b/src/library/scala/xml/parsing/ConstructingParser.scala index 623d2e3f37..962c629663 100644 --- a/src/library/scala/xml/parsing/ConstructingParser.scala +++ b/src/library/scala/xml/parsing/ConstructingParser.scala @@ -17,20 +17,13 @@ import java.io.File import scala.io.{ Source, Codec } object ConstructingParser { - - def fromFile(inp: File, preserveWS: Boolean) = { + def fromFile(inp: File, preserveWS: Boolean) = // XXX why does the default implicit not work here when building locker, // unless the empty parameter list is supplied? - val p = new ConstructingParser(Source.fromFile(inp)(), preserveWS) - p.nextch - p - } + new ConstructingParser(Source.fromFile(inp)(), preserveWS) initialize - def fromSource(inp: Source, preserveWS: Boolean) = { - val p = new ConstructingParser(inp, preserveWS) - p.nextch - p - } + def fromSource(inp: Source, preserveWS: Boolean) = + new ConstructingParser(inp, preserveWS) initialize } /** An xml parser. parses XML and invokes callback methods of a MarkupHandler. diff --git a/src/library/scala/xml/parsing/MarkupParser.scala b/src/library/scala/xml/parsing/MarkupParser.scala index a4af954e5a..15bd912c17 100644 --- a/src/library/scala/xml/parsing/MarkupParser.scala +++ b/src/library/scala/xml/parsing/MarkupParser.scala @@ -30,7 +30,9 @@ import Utility.Escapes.{ pairs => unescape } * @author Burak Emir * @version 1.0 */ -trait MarkupParser extends AnyRef with TokenTests { self: MarkupParser with MarkupHandler => +trait MarkupParser extends AnyRef with TokenTests +{ + self: MarkupParser with MarkupHandler => val input: Source @@ -239,6 +241,14 @@ trait MarkupParser extends AnyRef with TokenTests { self: MarkupParser with Mar //var xEmbeddedBlock = false; + /** As the current code requires you to call nextch once manually + * after construction, this method formalizes that suboptimal reality. + */ + def initialize: this.type = { + nextch + this + } + /** this method assign the next character to ch and advances in input */ def nextch { if (curInput.hasNext) { @@ -270,11 +280,7 @@ trait MarkupParser extends AnyRef with TokenTests { self: MarkupParser with Mar } } - def xToken(that: Seq[Char]): Unit = { - val it = that.iterator; - while (it.hasNext) - xToken(it.next); - } + def xToken(that: Seq[Char]): Unit = that foreach xToken /** parse attribute and create namespace scope, metadata * [41] Attributes ::= { S Name Eq AttValue } @@ -391,49 +397,26 @@ trait MarkupParser extends AnyRef with TokenTests { self: MarkupParser with Mar val pos1 = pos val sb: StringBuilder = new StringBuilder() while (true) { - if (ch==']' && - { sb.append(ch); nextch; ch == ']' } && - { sb.append(ch); nextch; ch == '>' } ) { - sb.length = sb.length - 2 - nextch; - return handle.text( pos1, sb.toString() ); - } else sb.append( ch ); + if (ch==']' && + { sb.append(ch); nextch; ch == ']' } && + { sb.append(ch); nextch; ch == '>' } ) { + sb.setLength(sb.length - 2); + nextch; + return PCData(sb.toString) + } else sb.append( ch ); nextch; } + // bq: (todo) increase grace when meeting CDATA section throw FatalError("this cannot happen"); - }; + } /** CharRef ::= "&#" '0'..'9' {'0'..'9'} ";" * | "&#x" '0'..'9'|'A'..'F'|'a'..'f' { hexdigit } ";" * * see [66] */ - def xCharRef(ch: () => Char, nextch: () => Unit): String = { + def xCharRef(ch: () => Char, nextch: () => Unit): String = Utility.parseCharRef(ch, nextch, reportSyntaxError _) - /* - val hex = (ch() == 'x') && { nextch(); true }; - val base = if (hex) 16 else 10; - var i = 0; - while (ch() != ';') { - ch() match { - case '0' | '1' | '2' | '3' | '4' | '5' | '6' | '7' | '8' | '9' => - i = i * base + Character.digit( ch(), base ); - case 'a' | 'b' | 'c' | 'd' | 'e' | 'f' - | 'A' | 'B' | 'C' | 'D' | 'E' | 'F' => - if (! hex) - reportSyntaxError("hex char not allowed in decimal char ref\n" - +"Did you mean to write &#x ?"); - else - i = i * base + Character.digit(ch(), base); - case _ => - reportSyntaxError("character '" + ch() + " not allowed in char ref\n"); - } - nextch(); - } - new String(Array(i.asInstanceOf[char])) - */ - } - /** Comment ::= '<!--' ((Char - '-') | ('-' (Char - '-')))* '-->' * @@ -441,8 +424,7 @@ trait MarkupParser extends AnyRef with TokenTests { self: MarkupParser with Mar */ def xComment: NodeSeq = { val sb: StringBuilder = new StringBuilder() - xToken('-') - xToken('-') + xToken("--") while (true) { if (ch == '-' && { sb.append(ch); nextch; ch == '-' }) { sb.length = sb.length - 1 @@ -933,7 +915,7 @@ trait MarkupParser extends AnyRef with TokenTests { self: MarkupParser with Mar case _ if isSpace(ch) => xSpace case _ => - reportSyntaxError("markupdecl: unexpected character '"+ch+"' #" + ch.asInstanceOf[Int]) + reportSyntaxError("markupdecl: unexpected character '"+ch+"' #" + ch.toInt) nextch } @@ -1097,22 +1079,9 @@ trait MarkupParser extends AnyRef with TokenTests { self: MarkupParser with Mar handle.notationDecl(notat, extID) } - /** - * report a syntax error - */ - def reportSyntaxError(pos: Int, str: String) { - curInput.reportError(pos, str) - //error("MarkupParser::synerr") // DEBUG - } - + def reportSyntaxError(pos: Int, str: String): Unit = curInput.reportError(pos, str) def reportSyntaxError(str: String): Unit = reportSyntaxError(pos, str) - - /** - * report a syntax error - */ - def reportValidationError(pos: Int, str: String) { - curInput.reportError(pos, str) - } + def reportValidationError(pos: Int, str: String): Unit = reportSyntaxError(pos, str) def push(entityName: String) { //Console.println("BEFORE PUSHING "+ch) @@ -1125,26 +1094,11 @@ trait MarkupParser extends AnyRef with TokenTests { self: MarkupParser with Mar nextch } - /* - def push(src:Source) = { - curInput = src - nextch - } - */ - def pushExternal(systemId: String) { - //Console.print("BEFORE PUSH, curInput = $"+curInput.descr) - //Console.println(" stack = "+inpStack.map { x => "$"+x.descr }) - - //Console.print("[PUSHING EXTERNAL "+systemId+"]") if (!eof) inpStack = curInput :: inpStack curInput = externalSource(systemId) - - //Console.print("AFTER PUSH, curInput = $"+curInput.descr) - //Console.println(" stack = "+inpStack.map { x => "$"+x.descr }) - nextch } @@ -1154,8 +1108,6 @@ trait MarkupParser extends AnyRef with TokenTests { self: MarkupParser with Mar ch = curInput.ch pos = curInput.pos eof = false // must be false, because of places where entity refs occur - //Console.println("\n AFTER POP, curInput = $"+curInput.descr); - //Console.println(inpStack.map { x => x.descr }); } /** for the moment, replace only character references diff --git a/src/library/scala/xml/parsing/XhtmlParser.scala b/src/library/scala/xml/parsing/XhtmlParser.scala index 1b395a2739..8132c00cf4 100644 --- a/src/library/scala/xml/parsing/XhtmlParser.scala +++ b/src/library/scala/xml/parsing/XhtmlParser.scala @@ -8,52 +8,19 @@ // $Id$ - package scala.xml package parsing import scala.io.Source /** <p> - * Extends the Markup Parser to do the right thing (tm) with PCData blocks. - * </p> - * <p> - * (c) David Pollak, 2007 WorldWide Conferencing, LLC. - * </p> - */ -trait PCDataMarkupParser[PCM <: MarkupParser with MarkupHandler] extends MarkupParser { self: PCM => - - /** '<! CharData ::= [CDATA[ ( {char} - {char}"]]>"{char} ) ']]>' - * - * see [15] - */ - override def xCharData: NodeSeq = { - xToken("[CDATA[") - val pos1 = pos - val sb: StringBuilder = new StringBuilder() - while (true) { - if (ch==']' && - { sb.append(ch); nextch; ch == ']' } && - { sb.append(ch); nextch; ch == '>' } ) { - sb.setLength(sb.length - 2); - nextch; - return PCData(sb.toString) - } else sb.append( ch ); - nextch; - } - // bq: (todo) increase grace when meeting CDATA section - throw FatalError("this cannot happen"); - } -} - -/** <p> * An XML Parser that preserves CDATA blocks and knows about HtmlEntities. * </p> * <p> * (c) David Pollak, 2007 WorldWide Conferencing, LLC. * </p> */ -class XhtmlParser(val input: Source) extends ConstructingHandler with PCDataMarkupParser[XhtmlParser] with ExternalSources { +class XhtmlParser(val input: Source) extends ConstructingHandler with MarkupParser with ExternalSources { val preserveWS = true ent ++= XhtmlEntities() } @@ -66,9 +33,5 @@ class XhtmlParser(val input: Source) extends ConstructingHandler with PCDataMark * </p> */ object XhtmlParser { - def apply(source: Source): NodeSeq = { - val p = new XhtmlParser(source) - p.nextch - p.document - } + def apply(source: Source): NodeSeq = new XhtmlParser(source).initialize.document } diff --git a/src/library/scala/xml/pull/XMLEventReader.scala b/src/library/scala/xml/pull/XMLEventReader.scala index c32bd81f4b..b09218a826 100644 --- a/src/library/scala/xml/pull/XMLEventReader.scala +++ b/src/library/scala/xml/pull/XMLEventReader.scala @@ -97,7 +97,7 @@ class XMLEventReader(src: Source) extends ProducerConsumerIterator[XMLEvent] override def run() { curInput = input - interruptibly { this.nextch ; this.document() } + interruptibly { this.initialize.document() } setEvent(POISON) } } diff --git a/test/files/jvm/unittest_xml.scala b/test/files/jvm/unittest_xml.scala index 63375cd15a..1569bb13af 100644 --- a/test/files/jvm/unittest_xml.scala +++ b/test/files/jvm/unittest_xml.scala @@ -2,14 +2,8 @@ object Test { import scala.testing.SUnit._ - import scala.xml.{MetaData, Null, Parsing, PrefixedAttribute, UnprefixedAttribute } + import scala.xml.{MetaData, Null, Utility, PrefixedAttribute, UnprefixedAttribute } - class ParsingTest extends TestCase("scala.xml.Parsing") with Assert { - override def runTest = { - assertTrue(Parsing.isNameStart('b')) - assertFalse(Parsing.isNameStart(':')) - } - } class MetaDataTest extends TestCase("scala.xml.MetaData") with Assert { import scala.xml.{HasKeyValue, TopScope, NamespaceBinding, Node, Atom, Text } @@ -65,6 +59,10 @@ object Test { class UtilityTest extends TestCase("scala.xml.Utility") with Assert { def runTest() = { + assertTrue(Utility.isNameStart('b')) + assertFalse(Utility.isNameStart(':')) + + val x = <foo> <toomuchws/> </foo> @@ -101,14 +99,11 @@ object Test { def main(args:Array[String]) = { val ts = new TestSuite( - new ParsingTest, new MetaDataTest, new UtilityTest ) val tr = new TestResult() ts.run(tr) - for(val failure <- tr.failures) { - Console.println(failure) - } + tr.failures foreach Console.println } } |