From 15d7342ea45a141171c6c80e7909b20638fdc3ad Mon Sep 17 00:00:00 2001
From: hns <hannesw@gmail.com>
Date: Mon, 3 Jun 2002 20:15:16 +0000
Subject: [PATCH] Switch to standard Java (JAXP) XML parser for
getXmlDocument() and provide our own HTML parser for getHtmlDocument which is
a thin bridge between javax.swing.text.html.parser.* and the Apache HTML-DOM
implementation.
---
src/helma/scripting/fesi/HopExtension.java | 42 +-----
src/helma/util/HtmlParser.java | 166 +++++++++++++++++++++
src/helma/util/XmlUtils.java | 78 ++++++++++
3 files changed, 251 insertions(+), 35 deletions(-)
create mode 100644 src/helma/util/HtmlParser.java
create mode 100644 src/helma/util/XmlUtils.java
diff --git a/src/helma/scripting/fesi/HopExtension.java b/src/helma/scripting/fesi/HopExtension.java
index 30134a2d..45460134 100644
--- a/src/helma/scripting/fesi/HopExtension.java
+++ b/src/helma/scripting/fesi/HopExtension.java
@@ -654,24 +654,9 @@ public class HopExtension {
}
public ESValue callFunction (ESObject thisObject, ESValue[] arguments) throws EcmaScriptException {
try {
- // Class.forName ("org.apache.xerces.parsers.DOMParser");
- // org.apache.xerces.parsers.DOMParser parser = new org.apache.xerces.parsers.DOMParser();
- Class.forName ("org.openxml.parser.XMLParser");
- org.openxml.parser.XMLParser parser = new org.openxml.parser.XMLParser();
Object p = arguments[0].toJavaObject ();
- if (p instanceof String) try {
- // first try to interpret string as URL
- java.net.URL u = new java.net.URL (p.toString ());
- parser.parse (p.toString());
- } catch (java.net.MalformedURLException nourl) {
- // if not a URL, maybe it is the XML itself
- parser.parse (new InputSource (new StringReader (p.toString())));
- }
- else if (p instanceof InputStream)
- parser.parse (new InputSource ((InputStream) p));
- else if (p instanceof Reader)
- parser.parse (new InputSource ((Reader) p));
- return ESLoader.normalizeObject (parser.getDocument(), evaluator);
+ Object doc = helma.util.XmlUtils.parseXml (p);
+ return ESLoader.normalizeObject (doc, evaluator);
} catch (Exception noluck) {
app.logEvent ("Error creating XML document: "+noluck);
}
@@ -685,22 +670,9 @@ public class HopExtension {
}
public ESValue callFunction (ESObject thisObject, ESValue[] arguments) throws EcmaScriptException {
try {
- Class.forName ("org.openxml.parser.HTMLParser");
- org.openxml.parser.HTMLParser parser = new org.openxml.parser.HTMLParser();
Object p = arguments[0].toJavaObject ();
- if (p instanceof String) try {
- // first try to interpret string as URL
- java.net.URL u = new java.net.URL (p.toString ());
- parser.parse (p.toString());
- } catch (java.net.MalformedURLException nourl) {
- // if not a URL, maybe it is the HTML itself
- parser.parse (new InputSource (new StringReader (p.toString())));
- }
- else if (p instanceof InputStream)
- parser.parse (new InputSource ((InputStream) p));
- else if (p instanceof Reader)
- parser.parse (new InputSource ((Reader) p));
- return ESLoader.normalizeObject (parser.getDocument(), evaluator);
+ Object doc = helma.util.XmlUtils.parseHtml (p);
+ return ESLoader.normalizeObject (doc, evaluator);
} catch (Exception noluck) {
app.logEvent ("Error creating HTML document: "+noluck);
}
@@ -714,13 +686,13 @@ public class HopExtension {
}
public ESValue callFunction (ESObject thisObject, ESValue[] arguments) throws EcmaScriptException {
try {
- Class.forName ("org.w3c.dom.Document");
+ Class.forName ("org.w3c.dom.Document");
org.w3c.dom.Document doc = (org.w3c.dom.Document) arguments[0].toJavaObject ();
Class.forName ("org.jdom.input.DOMBuilder");
- org.jdom.input.DOMBuilder builder = new org.jdom.input.DOMBuilder ();
+ org.jdom.input.DOMBuilder builder = new org.jdom.input.DOMBuilder ();
return ESLoader.normalizeObject (builder.build (doc), evaluator);
} catch (Exception noluck) {
- app.logEvent ("Error wrapping JDOM document: "+noluck);
+ app.logEvent ("Error building JDOM document: "+noluck);
}
return ESNull.theNull;
}
diff --git a/src/helma/util/HtmlParser.java b/src/helma/util/HtmlParser.java
new file mode 100644
index 00000000..2341aa5f
--- /dev/null
+++ b/src/helma/util/HtmlParser.java
@@ -0,0 +1,166 @@
+// HtmlParser.java
+// Copyright (c) Hannes Walln�fer 2002
+
+package helma.util;
+
+import java.util.HashMap;
+import java.util.ArrayList;
+import java.util.Enumeration;
+import java.io.IOException;
+import javax.swing.text.html.parser.*;
+import javax.swing.text.SimpleAttributeSet;
+import org.xml.sax.SAXException;
+import org.apache.html.dom.*;
+import org.w3c.dom.html.HTMLDocument;
+
+public class HtmlParser extends Parser {
+
+ HTMLBuilder builder;
+ Attributes attributes = new Attributes ();
+
+ public HtmlParser () throws IOException {
+ super (DTD.getDTD ("html32"));
+ dtd.getElement ("table");
+ dtd.getElement ("tr");
+ dtd.getElement ("td");
+ dtd.getElement ("span");
+ dtd.getElement ("div");
+ dtd.getElement ("font");
+ dtd.getElement ("b");
+ dtd.getElement ("i");
+ dtd.getElement ("a");
+ dtd.getElement ("blockquote");
+ dtd.getElement ("em");
+ dtd.getElement ("ul");
+ dtd.getElement ("ol");
+ dtd.getElement ("li");
+ dtd.elementHash.remove ("meta");
+ dtd.elementHash.remove ("link");
+ dtd.elementHash.remove ("base");
+ builder = new HTMLBuilder ();
+ try {
+ builder.startDocument ();
+ } catch (SAXException x) {
+ System.err.println ("Error in constructor");
+ }
+ }
+
+ /**
+ * Handle Start Tag.
+ */
+ protected void handleStartTag(TagElement tag) {
+ // System.err.println ("handleStartTag ("+tag.getHTMLTag()+")");
+ attributes.convert (getAttributes());
+ flushAttributes();
+ try {
+ builder.startElement (tag.getHTMLTag().toString().toUpperCase(), attributes);
+ } catch (SAXException x) {
+ System.err.println ("Error in handleStartTag");
+ }
+ }
+
+ /**
+ * Handle Empty Tag.
+ */
+ protected void handleEmptyTag(TagElement tag) {
+ // System.err.println ("handleEmptyTag ("+tag.getHTMLTag()+")");
+ attributes.convert (getAttributes());
+ flushAttributes();
+ try {
+ builder.startElement (tag.getHTMLTag().toString().toUpperCase(), attributes);
+ builder.endElement (tag.getHTMLTag().toString().toUpperCase());
+ } catch (SAXException x) {
+ System.err.println ("Error in handleEmptyTag: "+x);
+ }
+ }
+
+ /**
+ * Handle End Tag.
+ */
+ protected void handleEndTag(TagElement tag) {
+ // System.err.println ("handleEndTag ("+tag.getHTMLTag()+")");
+ try {
+ builder.endElement (tag.getHTMLTag().toString().toUpperCase());
+ } catch (SAXException x) {
+ System.err.println ("Error in handleEndTag: "+x);
+ }
+ }
+
+ /**
+ * Handle Text.
+ */
+ protected void handleText(char data[]) {
+ // System.err.println ("handleText ("+new String (data)+")");
+ try {
+ builder.characters (data, 0, data.length);
+ } catch (SAXException x) {
+ System.err.println ("Error in handleText");
+ }
+ }
+
+ /*
+ * Error handling.
+ */
+ protected void handleError(int ln, String errorMsg) {
+ // System.err.println ("handleError ("+ln+": "+errorMsg+")");
+ }
+
+ /**
+ * Handle comment.
+ */
+ protected void handleComment(char text[]) {
+ }
+
+ public HTMLDocument getDocument () {
+ try {
+ builder.endDocument ();
+ } catch (SAXException x) {}
+ return builder.getHTMLDocument ();
+ }
+
+
+ class Attributes implements org.xml.sax.AttributeList {
+ HashMap map = new HashMap();
+ ArrayList names = new ArrayList();
+ ArrayList values = new ArrayList ();
+
+ public int getLength() {
+ return names.size();
+ }
+
+ public String getName (int i) {
+ return (String) names.get (i);
+ }
+
+ public String getType (int i) {
+ return "CDATA";
+ }
+
+ public String getType (String name) {
+ return "CDATA";
+ }
+
+ public String getValue (int i) {
+ return (String) values.get (i);
+ }
+
+ public String getValue (String name) {
+ return (String) map.get (name);
+ }
+
+ public void convert (SimpleAttributeSet attset) {
+ map.clear ();
+ names.clear ();
+ values.clear ();
+ for (Enumeration e = attset.getAttributeNames(); e.hasMoreElements(); ) {
+ Object name = e.nextElement ();
+ Object value = attset.getAttribute (name).toString();
+ map.put (name.toString(), value);
+ names.add (name.toString());
+ values.add (value);
+ }
+ }
+
+ }
+}
+
diff --git a/src/helma/util/XmlUtils.java b/src/helma/util/XmlUtils.java
new file mode 100644
index 00000000..918ebcb1
--- /dev/null
+++ b/src/helma/util/XmlUtils.java
@@ -0,0 +1,78 @@
+package helma.util;
+
+import java.io.InputStream;
+import java.io.IOException;
+import java.io.Reader;
+import java.io.StringReader;
+import java.io.InputStreamReader;
+import java.net.URL;
+import java.net.MalformedURLException;
+
+import javax.xml.parsers.DocumentBuilderFactory;
+import javax.xml.parsers.DocumentBuilder;
+import javax.xml.parsers.SAXParserFactory;
+import javax.xml.parsers.SAXParser;
+import javax.xml.parsers.ParserConfigurationException;
+import javax.xml.parsers.ParserConfigurationException;
+
+import org.w3c.dom.Document;
+import org.xml.sax.Parser;
+import org.xml.sax.InputSource;
+import org.xml.sax.SAXException;
+
+
+public class XmlUtils {
+
+ private static DocumentBuilderFactory domBuilderFactory = null;
+ private static SAXParserFactory saxParserFactory = null;
+
+ public static Document parseXml (Object obj)
+ throws SAXException, IOException, ParserConfigurationException {
+ if (domBuilderFactory == null)
+ domBuilderFactory = javax.xml.parsers.DocumentBuilderFactory.newInstance();
+ DocumentBuilder parser = domBuilderFactory.newDocumentBuilder();
+ Document doc = null;
+ if (obj instanceof String) try {
+ // first try to interpret string as URL
+ URL url = new URL (obj.toString ());
+ doc = parser.parse (obj.toString());
+ } catch (MalformedURLException nourl) {
+ // if not a URL, maybe it is the XML itself
+ doc = parser.parse (new InputSource (new StringReader (obj.toString())));
+ } else if (obj instanceof InputStream) {
+ doc = parser.parse (new InputSource ((InputStream) obj));
+ } else if (obj instanceof Reader) {
+ doc = parser.parse (new InputSource ((Reader) obj));
+ }
+ doc.normalize();
+ return doc;
+ }
+
+
+ public static Document parseHtml (Object obj)
+ throws SAXException, IOException, ParserConfigurationException {
+ try {
+ Class.forName ("org.apache.html.dom.HTMLBuilder");
+ } catch (Throwable notfound) {
+ throw new IOException ("Couldn't load nekohtml/Xerces HTML parser: "+notfound);
+ }
+ Document doc = null;
+ HtmlParser parser = new HtmlParser ();
+ if (obj instanceof String) try {
+ // first try to interpret string as URL
+ URL url = new URL (obj.toString ());
+ parser.parse (new InputStreamReader (url.openStream()));
+ } catch (MalformedURLException nourl) {
+ // if not a URL, maybe it is the XML itself
+ parser.parse (new StringReader (obj.toString()));
+ } else if (obj instanceof InputStream) {
+ parser.parse (new InputStreamReader ((InputStream) obj));
+ } else if (obj instanceof Reader) {
+ parser.parse ((Reader) obj);
+ }
+ doc = parser.getDocument ();
+ return doc;
+ }
+
+
+}