advanced.tex

来自「Nano的XML解析器」· TEX 代码 · 共 483 行 · 第 1/2 页

~~~~\xkeyword{this}.children = \xkeyword{new} Vector();
~~\}
~
~~\xkeyword{public void} setAttribute(String attrName,
~~~~~~~~~~~~~~~~~~~~~~~~~~~String value)
~~\{
~~~~\xkeyword{this}.attrs.put(attrName, value);
~~\}
~
~~\xkeyword{public void} addChild(DocumentElement elt)
~~\{
~~~~\xkeyword{this}.children.addElement(elt);
~~\}
\}
\end{example}

This base class simply makes it easy for our builder to set attributes and to add children to an element.

The \classname{Chapter} and \classname{Paragraph} classes extend this base class to give more practical access to their attributes and children:

\begin{example}
\xkeyword{public class} Chapter
~~\xkeyword{extends} DocumentElement
\{
~~\xkeyword{public} String getTitle()
~~\{
~~~~\xkeyword{return this}.attrs.getProperty("title");
~~\}
~
~~\xkeyword{public} String getID()
~~\{
~~~~\xkeyword{return this}.attrs.getProperty("id");
~~\}
~
~~\xkeyword{public} Enumeration getParagraphs()
~~\{
~~~~\xkeyword{return this}.children.elements();
~~\}
\}
~
\xkeyword{public class} Paragraph
~~\xkeyword{extends} DocumentElement
\{
~~\xkeyword{public static final int} LEFT = 0;
~~\xkeyword{public static final int} CENTER = 1;
~~\xkeyword{public static final int} RIGHT = 2;
~
~~\xkeyword{private static} Hashtable alignments;
~
~~\xkeyword{static}
~~\{
~~~~alignments = \xkeyword{new} Hashtable();
~~~~alignments.put("left", \xkeyword{new} Integer(LEFT));
~~~~alignments.put("center", \xkeyword{new} Integer(CENTER));
~~~~alignments.put("right", \xkeyword{new} Integer(RIGHT));
~~\}
~
~~\xkeyword{public} String getContent()
~~\{
~~~~\xkeyword{return this}.attrs.getProperty("\#PCDATA");
~~\}
~
~~\xkeyword{public int} getAlignment()
~~\{
~~~~String str = \xkeyword{this}.attrs.getProperty("align");
~~~~Integer align = alignments.get(str);
~~~~\xkeyword{return} align.intValue();
~~\}
\}
\end{example}

The builder creates the data structure based on the \XML{} events it receives from the parser.
Because both \classname{Chapter} and \classname{Paragraph} extend \classname{DocumentElement}, the builder is fairly simple.

\begin{example}
\xkeyword{import} net.n3.nanoxml.*;
\xkeyword{import} java.util.*;
\xkeyword{import} java.io.*;
~
\xkeyword{public class} DocumentBuilder
~~\xkeyword{implements} IXMLBuilder
\{
~~\xkeyword{private static} Hashtable classes;
~~\xkeyword{private} Stack elements;
~~\xkeyword{private} DocumentElement topElement;
~
~~\xkeyword{static}
~~\{
~~~~classes = \xkeyword{new} Hashtable();
~~~~classes.put("Chapter", Chapter.\xkeyword{class});
~~~~classes.put("Paragraph", Paragraph.\xkeyword{class});
~~\}
~
~~\xkeyword{public void} startBuilding(String systemID,
~~~~~~~~~~~~~~~~~~~~~~~~~~~~\xkeyword{int} lineNr)
~~\{
~~~~\xkeyword{this}.elements = \xkeyword{new} Stack();
~~~~\xkeyword{this}.topElement = \xkeyword{null};
~~\}
~
~~\xkeyword{public void} newProcessingInstruction(String target,
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~Reader reader)
~~\{
~~~~// nothing to do
~~\}
~
~~\xkeyword{public void} startElement(String name,
~~~~~~~~~~~~~~~~~~~~~~~~~~~String nsPrefix,
~~~~~~~~~~~~~~~~~~~~~~~~~~~String nsSystemID,
~~~~~~~~~~~~~~~~~~~~~~~~~~~String systemID,
~~~~~~~~~~~~~~~~~~~~~~~~~~~\xkeyword{int} lineNr)
~~\{
~~~~DocumentElement elt = \xkeyword{null};
~~~~\xkeyword{try} \{
~~~~~~Class cls = (Class) classes.get(name);
~~~~~~elt = (DocumentElement) cls.newInstance();
~~~~\} \xkeyword{catch} (Exception e) \{
~~~~~~// ignore the exception
~~~~\}
~~~~\xkeyword{this}.elements.push(elt);
~~~~\xkeyword{if} (\xkeyword{this}.topElement == \xkeyword{null}) \{
~~~~~~\xkeyword{this}.topElement = elt;
~~~~\}
~~\}
~
~~\xkeyword{public void} endElement(String name,
~~~~~~~~~~~~~~~~~~~~~~~~~String nsPrefix,
~~~~~~~~~~~~~~~~~~~~~~~~~String nsSystemID)
~~\{
~~~~DocumentElement child = (DocumentElement) \xkeyword{this}.elements.pop();
~~~~\xkeyword{if} (! \xkeyword{this}.elements.isEmpty()) \{
~~~~~~DocumentElement parent = (DocumentElement) \xkeyword{this}.elements.peek();
~~~~~~parent.addChild(child);
~~~~\}
~~\}
~
~~\xkeyword{public void} addAttribute(String key,
~~~~~~~~~~~~~~~~~~~~~~~~~~~String nsPrefix,
~~~~~~~~~~~~~~~~~~~~~~~~~~~String nsSystemID,
~~~~~~~~~~~~~~~~~~~~~~~~~~~String value,
~~~~~~~~~~~~~~~~~~~~~~~~~~~String type)
~~\{
~~~~DocumentElement child = (DocumentElement) \xkeyword{this}.elements.peek();
~~~~child.setAttribute(key, value);
~~\}
~
~~\xkeyword{public void} elementAttributesProcessed(String name,
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~String nsPrefix,
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~String nsSystemID)
~~\{
~~~~// nothing to do
~~\}
~
~~\xkeyword{public void} addPCData(Reader reader,
~~~~~~~~~~~~~~~~~~~~~~~~String systemID,
~~~~~~~~~~~~~~~~~~~~~~~~\xkeyword{int} lineNr)
~~~~\xkeyword{throws} IOException
~~\{
~~~~StringBuffer str = \xkeyword{new} StringBuffer(1024);
~~~~\xkeyword{char}[] buf = \xkeyword{new char}[bufSize];
~~~~\xkeyword{for} (;;) \{
~~~~~~\xkeyword{int} size = reader.read(buf);
~~~~~~\xkeyword{if} (size < 0) \{
~~~~~~~~\xkeyword{break};
~~~~~~\}
~~~~~~str.append(buf, 0, size);
~~~~\}
~~~~\xkeyword{this}.addAttribute("\#PCDATA", \xkeyword{null}, \xkeyword{null}, str.toString(), "CDATA");
~~\}
~
~~\xkeyword{public} Object getResult()
~~\{
~~~~\xkeyword{return} topElement;
~~\}
\}
\end{example}

Note that, for simplicity, error and exception handling is not present in this example.
The builder holds a stack of the current elements it builds.
Character data is read from a reader.
The method \methodname{addPCData} reads this data in blocks of 1K.

Finally, this application sets up the \NanoXML{} parser and converts an \XML{} document to \ltext{HTML} which it dumps on the standard output:

\begin{example}
\xkeyword{import} java.util.*;
\xkeyword{import} net.n3.nanoxml.*;
~
\xkeyword{public class} XML2HTML
\{
~~\xkeyword{public static void} main(String[] params)
~~~~\xkeyword{throws} Exception
~~\{
~~~~IXMLBuilder builder = \xkeyword{new} DocumentBuilder();
~~~~IXMLParser parser = XMLParserFactory.createDefaultXMLParser();
~~~~parser.setBuilder(builder);
~~~~IXMLReader reader = StdXMLReader.fileReader(param[0]);
~~~~parser.setReader(reader);
~~~~Chapter chapter = (Chapter) parser.parse();
~~~~System.out.println("$<$!DOCTYPE \ldots{} $>$");
~~~~System.out.print("$<$HTML$><$HEAD$><$TITLE$>$");
~~~~System.out.print(chapter.getTitle());
~~~~System.out.println("</TITLE></HEAD><BODY>");
~~~~System.out.print("$<$H1$>$");
~~~~System.out.print(chapter.getTitle());
~~~~System.out.println("$<$/H1$>$");
~~~~Enumeration enum = chapter.getParagraphs();
~~~~\xkeyword{while} (enum.hasMoreElements()) \{
~~~~~~Paragraph para = (Paragraph) enum.nextElement();
~~~~~~System.out.print("$<$P$>$");
~~~~~~System.out.print(para.getContent());
~~~~~~System.out.println("$<$/P$>$");
~~~~\}
~~~~System.out.println("$<$/BODY$><$/HTML$>$");
~~\}
\}
\end{example}

If we run the example on the following \XML{} file:

\begin{example}
$<$!DOCTYPE Chapter SYSTEM "document.dtd"$>$
~
$<$Chapter id="ch01" title="The Title"$>$
~~~~$<$Paragraph$>$First paragraph...$<$/Paragraph$>$
~~~~$<$Paragraph$>$Second paragraph...$<$/Paragraph$>$
$<$/Chapter$>$
\end{example}

The output will be:

\begin{example}
$<$!DOCTYPE HTML PUBLIC '-//W3C//DTD HTML 4.01//EN'
~~'http://www.w3.org/TR/html4/strict.dtd'>
$<$HTML$><$HEAD$><$TITLE$>$The Title$<$/TITLE$><$/HEAD$><$BODY$>$
$<$H1$>$The Title$<$/H1$>$
$<$P$>$First paragraph...$<$/P$>$
$<$P$>$Second paragraph...$<$/P$>$
$<$/BODY$>$
\end{example}