net.sf.saxon.event.HTMLEmitter Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of saxon9 Show documentation
Show all versions of saxon9 Show documentation
Provides a basic XSLT 2.0 and XQuery 1.0 processor (W3C Recommendations,
January 2007). Command line interfaces and implementations of several
Java APIs (DOM, XPath, s9api) are also included.
The newest version!
package net.sf.saxon.event;
import net.sf.saxon.tinytree.CompressedWhitespace;
import net.sf.saxon.trans.XPathException;
import net.sf.saxon.value.Whitespace;
import javax.xml.transform.OutputKeys;
/**
* This class generates HTML output
* @author Michael H. Kay
*/
public class HTMLEmitter extends XMLEmitter {
/**
* Preferred character representations
*/
private static final int REP_NATIVE = 0;
private static final int REP_ENTITY = 1;
private static final int REP_DECIMAL = 2;
private static final int REP_HEX = 3;
private int nonASCIIRepresentation = REP_NATIVE;
private int excludedRepresentation = REP_ENTITY;
private int inScript;
private boolean started = false;
private String elementName;
private short uriCode;
/**
* Decode preferred representation
* @param rep string containing preferred representation (native, entity, decimal, or hex)
* @return integer code for the preferred representation
*/
private static int representationCode(String rep) {
if (rep.equalsIgnoreCase("native")) return REP_NATIVE;
if (rep.equalsIgnoreCase("entity")) return REP_ENTITY;
if (rep.equalsIgnoreCase("decimal")) return REP_DECIMAL;
if (rep.equalsIgnoreCase("hex")) return REP_HEX;
return REP_ENTITY;
}
/**
* Table of HTML tags that have no closing tag
*/
static HTMLTagHashSet emptyTags = new HTMLTagHashSet(31);
static {
setEmptyTag("area");
setEmptyTag("base");
setEmptyTag("basefont");
setEmptyTag("br");
setEmptyTag("col");
setEmptyTag("frame");
setEmptyTag("hr");
setEmptyTag("img");
setEmptyTag("input");
setEmptyTag("isindex");
setEmptyTag("link");
setEmptyTag("meta");
setEmptyTag("param");
}
private static void setEmptyTag(String tag) {
emptyTags.add(tag);
}
protected static boolean isEmptyTag(String tag) {
return emptyTags.contains(tag);
}
/**
* Table of boolean attributes
*/
// we use two HashMaps to avoid unnecessary string concatenations
private static HTMLTagHashSet booleanAttributes = new HTMLTagHashSet(31);
private static HTMLTagHashSet booleanCombinations = new HTMLTagHashSet(53);
static {
setBooleanAttribute("area", "nohref");
setBooleanAttribute("button", "disabled");
setBooleanAttribute("dir", "compact");
setBooleanAttribute("dl", "compact");
setBooleanAttribute("frame", "noresize");
setBooleanAttribute("hr", "noshade");
setBooleanAttribute("img", "ismap");
setBooleanAttribute("input", "checked");
setBooleanAttribute("input", "disabled");
setBooleanAttribute("input", "readonly");
setBooleanAttribute("menu", "compact");
setBooleanAttribute("object", "declare");
setBooleanAttribute("ol", "compact");
setBooleanAttribute("optgroup", "disabled");
setBooleanAttribute("option", "selected");
setBooleanAttribute("option", "disabled");
setBooleanAttribute("script", "defer");
setBooleanAttribute("select", "multiple");
setBooleanAttribute("select", "disabled");
setBooleanAttribute("td", "nowrap");
setBooleanAttribute("textarea", "disabled");
setBooleanAttribute("textarea", "readonly");
setBooleanAttribute("th", "nowrap");
setBooleanAttribute("ul", "compact");
}
private static void setBooleanAttribute(String element, String attribute) {
booleanAttributes.add(attribute);
booleanCombinations.add(element + '+' + attribute);
}
private static boolean isBooleanAttribute(String element, String attribute, String value) {
return attribute.equalsIgnoreCase(value) &&
booleanAttributes.contains(attribute) &&
booleanCombinations.contains(element + '+' + attribute);
}
/**
* Constructor
*/
public HTMLEmitter() {
}
/**
* Output start of document
*/
public void open() throws XPathException {}
protected void openDocument() throws XPathException {
if (writer==null) {
makeWriter();
}
if (started) return;
started = true;
// This method is sometimes called twice, especially during an identity transform
// This check stops two DOCTYPE declarations being output.
String version = outputProperties.getProperty(OutputKeys.VERSION);
if (version != null && !(version.equals("4.0") || version.equals("4.01"))) {
XPathException err = new XPathException("Unsupported HTML version: " + version);
err.setErrorCode("SESU0013");
throw err;
}
String byteOrderMark = outputProperties.getProperty(SaxonOutputKeys.BYTE_ORDER_MARK);
if ("yes".equals(byteOrderMark) &&
"UTF-8".equalsIgnoreCase(outputProperties.getProperty(OutputKeys.ENCODING))) {
try {
writer.write('\uFEFF');
} catch (java.io.IOException err) {
// Might be an encoding exception; just ignore it
}
}
String systemId = outputProperties.getProperty(OutputKeys.DOCTYPE_SYSTEM);
String publicId = outputProperties.getProperty(OutputKeys.DOCTYPE_PUBLIC);
if (systemId!=null || publicId!=null) {
writeDocType("html", systemId, publicId);
}
empty = false;
inScript = -1000000;
// Handle saxon:character-representation
String representation = outputProperties.getProperty(
SaxonOutputKeys.CHARACTER_REPRESENTATION);
if (representation != null) {
String nonASCIIrep;
String excludedRep;
int semi = representation.indexOf(';');
if (semi < 0) {
nonASCIIrep = Whitespace.trim(representation);
excludedRep = nonASCIIrep;
} else {
nonASCIIrep = Whitespace.trim(representation.substring(0, semi));
excludedRep = Whitespace.trim(representation.substring(semi+1));
}
nonASCIIRepresentation = representationCode(nonASCIIrep);
excludedRepresentation = representationCode(excludedRep);
if (excludedRepresentation == REP_NATIVE) {
excludedRepresentation = REP_ENTITY;
}
}
}
/**
* Output element start tag
*/
public void startElement(int nameCode, int typeCode, int locationId, int properties) throws XPathException {
super.startElement(nameCode, typeCode, locationId, properties);
uriCode = namePool.getURICode(nameCode);
elementName = (String)elementStack.peek();
if (uriCode==0 &&
( elementName.equalsIgnoreCase("script") ||
elementName.equalsIgnoreCase("style"))) {
inScript = 0;
}
inScript++;
}
public void startContent() throws XPathException {
closeStartTag(); // prevent ') {
writer.write(">"); // changed to allow for "]]>"
} else if (c=='&') {
writer.write("&");
}
}
} else if (c==160) {
// always output NBSP as an entity reference
writer.write(" ");
} else if (c>=127 && c<160) {
// these control characters are illegal in HTML
XPathException err = new XPathException("Illegal HTML character: decimal " + (int)c);
err.setErrorCode("SERE0014");
throw err;
} else if (c>=55296 && c<=56319) { //handle surrogate pair
//A surrogate pair is two consecutive Unicode characters. The first
//is in the range D800 to DBFF, the second is in the range DC00 to DFFF.
//To compute the numeric value of the character corresponding to a surrogate
//pair, use this formula (all numbers are hex):
//(FirstChar - D800) * 400 + (SecondChar - DC00) + 10000
// we'll trust the data to be sound
int charval = (((int)c - 55296) * 1024) + ((int)chars.charAt(i+1) - 56320) + 65536;
outputCharacterReference(charval);
i++;
} else if (characterSet.inCharset(c)) {
switch(nonASCIIRepresentation) {
case REP_NATIVE:
writer.write(c);
break;
case REP_ENTITY:
if (c>160 && c<=255) {
// if chararacter in iso-8859-1, use an entity reference
writer.write('&');
writer.write(latin1Entities[(int)c-160]);
writer.write(';');
break;
}
// else fall through
case REP_DECIMAL:
preferHex = false;
outputCharacterReference(c);
break;
case REP_HEX:
preferHex = true;
// fall through
default:
outputCharacterReference(c);
break;
}
} else {
// Character not present in encoding
switch(excludedRepresentation) {
case REP_ENTITY:
if (c>160 && c<=255) {
// if chararacter in iso-8859-1, use an entity reference
writer.write('&');
writer.write(latin1Entities[(int)c-160]);
writer.write(';');
break;
}
// else fall through
case REP_NATIVE:
case REP_DECIMAL:
preferHex = false;
outputCharacterReference(c);
break;
case REP_HEX:
preferHex = true;
// fall through
default:
outputCharacterReference(c);
break;
}
}
segstart = ++i;
}
}
/**
* Output an element end tag.
*/
public void endElement() throws XPathException {
String name = (String)elementStack.peek();
inScript--;
if (inScript==0) {
inScript = -1000000;
}
if (isEmptyTag(name) && uriCode==0) {
// no end tag required
elementStack.pop();
} else {
super.endElement();
}
}
/**
* Character data.
*/
public void characters (CharSequence chars, int locationId, int properties)
throws XPathException {
int options = properties;
if (inScript>0) {
options |= ReceiverOptions.DISABLE_ESCAPING;
}
super.characters(chars, locationId, options);
}
/**
* Handle a processing instruction.
*/
public void processingInstruction (String target, CharSequence data, int locationId, int properties)
throws XPathException
{
if (empty) {
openDocument();
}
for (int i=0; i') {
XPathException err = new XPathException("A processing instruction in HTML must not contain a > character");
err.setErrorCode("SERE0015");
throw err;
}
}
try {
writer.write("');
} catch (java.io.IOException err) {
throw new XPathException(err);
}
}
private static final String[] latin1Entities = {
"nbsp", // " " -- no-break space = non-breaking space,
// U+00A0 ISOnum -->
"iexcl", // "¡" -- inverted exclamation mark, U+00A1 ISOnum -->
"cent", // "¢" -- cent sign, U+00A2 ISOnum -->
"pound", // "£" -- pound sign, U+00A3 ISOnum -->
"curren", // "¤" -- currency sign, U+00A4 ISOnum -->
"yen", // "¥" -- yen sign = yuan sign, U+00A5 ISOnum -->
"brvbar", // "¦" -- broken bar = broken vertical bar,
// U+00A6 ISOnum -->
"sect", // "§" -- section sign, U+00A7 ISOnum -->
"uml", // "¨" -- diaeresis = spacing diaeresis,
// U+00A8 ISOdia -->
"copy", // "©" -- copyright sign, U+00A9 ISOnum -->
"ordf", // "ª" -- feminine ordinal indicator, U+00AA ISOnum -->
"laquo", // "«" -- left-pointing double angle quotation mark
// = left pointing guillemet, U+00AB ISOnum -->
"not", // "¬" -- not sign, U+00AC ISOnum -->
"shy", // "" -- soft hyphen = discretionary hyphen,
// U+00AD ISOnum -->
"reg", // "®" -- registered sign = registered trade mark sign,
// U+00AE ISOnum -->
"macr", // "¯" -- macron = spacing macron = overline
// = APL overbar, U+00AF ISOdia -->
"deg", // "°" -- degree sign, U+00B0 ISOnum -->
"plusmn", // "±" -- plus-minus sign = plus-or-minus sign,
// U+00B1 ISOnum -->
"sup2", // "²" -- superscript two = superscript digit two
// = squared, U+00B2 ISOnum -->
"sup3", // "³" -- superscript three = superscript digit three
// = cubed, U+00B3 ISOnum -->
"acute", // "´" -- acute accent = spacing acute,
// U+00B4 ISOdia -->
"micro", // "µ" -- micro sign, U+00B5 ISOnum -->
"para", // "¶" -- pilcrow sign = paragraph sign,
// U+00B6 ISOnum -->
"middot", // "·" -- middle dot = Georgian comma
// = Greek middle dot, U+00B7 ISOnum -->
"cedil", // "¸" -- cedilla = spacing cedilla, U+00B8 ISOdia -->
"sup1", // "¹" -- superscript one = superscript digit one,
// U+00B9 ISOnum -->
"ordm", // "º" -- masculine ordinal indicator,
// U+00BA ISOnum -->
"raquo", // "»" -- right-pointing double angle quotation mark
// = right pointing guillemet, U+00BB ISOnum -->
"frac14", // "¼" -- vulgar fraction one quarter
// = fraction one quarter, U+00BC ISOnum -->
"frac12", // "½" -- vulgar fraction one half
// = fraction one half, U+00BD ISOnum -->
"frac34", // "¾" -- vulgar fraction three quarters
// = fraction three quarters, U+00BE ISOnum -->
"iquest", // "¿" -- inverted question mark
// = turned question mark, U+00BF ISOnum -->
"Agrave", // "À" -- latin capital letter A with grave
// = latin capital letter A grave,
// U+00C0 ISOlat1 -->
"Aacute", // "Á" -- latin capital letter A with acute,
// U+00C1 ISOlat1 -->
"Acirc", // "Â" -- latin capital letter A with circumflex,
// U+00C2 ISOlat1 -->
"Atilde", // "Ã" -- latin capital letter A with tilde,
// U+00C3 ISOlat1 -->
"Auml", // "Ä" -- latin capital letter A with diaeresis,
// U+00C4 ISOlat1 -->
"Aring", // "Å" -- latin capital letter A with ring above
// = latin capital letter A ring,
// U+00C5 ISOlat1 -->
"AElig", // "Æ" -- latin capital letter AE
// = latin capital ligature AE,
// U+00C6 ISOlat1 -->
"Ccedil", // "Ç" -- latin capital letter C with cedilla,
// U+00C7 ISOlat1 -->
"Egrave", // "È" -- latin capital letter E with grave,
// U+00C8 ISOlat1 -->
"Eacute", // "É" -- latin capital letter E with acute,
// U+00C9 ISOlat1 -->
"Ecirc", // "Ê" -- latin capital letter E with circumflex,
// U+00CA ISOlat1 -->
"Euml", // "Ë" -- latin capital letter E with diaeresis,
// U+00CB ISOlat1 -->
"Igrave", // "Ì" -- latin capital letter I with grave,
// U+00CC ISOlat1 -->
"Iacute", // "Í" -- latin capital letter I with acute,
// U+00CD ISOlat1 -->
"Icirc", // "Î" -- latin capital letter I with circumflex,
// U+00CE ISOlat1 -->
"Iuml", // "Ï" -- latin capital letter I with diaeresis,
// U+00CF ISOlat1 -->
"ETH", // "Ð" -- latin capital letter ETH, U+00D0 ISOlat1 -->
"Ntilde", // "Ñ" -- latin capital letter N with tilde,
// U+00D1 ISOlat1 -->
"Ograve", // "Ò" -- latin capital letter O with grave,
// U+00D2 ISOlat1 -->
"Oacute", // "Ó" -- latin capital letter O with acute,
// U+00D3 ISOlat1 -->
"Ocirc", // "Ô" -- latin capital letter O with circumflex,
// U+00D4 ISOlat1 -->
"Otilde", // "Õ" -- latin capital letter O with tilde,
// U+00D5 ISOlat1 -->
"Ouml", // "Ö" -- latin capital letter O with diaeresis,
// U+00D6 ISOlat1 -->
"times", // "×" -- multiplication sign, U+00D7 ISOnum -->
"Oslash", // "Ø" -- latin capital letter O with stroke
// = latin capital letter O slash,
// U+00D8 ISOlat1 -->
"Ugrave", // "Ù" -- latin capital letter U with grave,
// U+00D9 ISOlat1 -->
"Uacute", // "Ú" -- latin capital letter U with acute,
// U+00DA ISOlat1 -->
"Ucirc", // "Û" -- latin capital letter U with circumflex,
// U+00DB ISOlat1 -->
"Uuml", // "Ü" -- latin capital letter U with diaeresis,
// U+00DC ISOlat1 -->
"Yacute", // "Ý" -- latin capital letter Y with acute,
// U+00DD ISOlat1 -->
"THORN", // "Þ" -- latin capital letter THORN,
// U+00DE ISOlat1 -->
"szlig", // "ß" -- latin small letter sharp s = ess-zed,
// U+00DF ISOlat1 -->
"agrave", // "à" -- latin small letter a with grave
// = latin small letter a grave,
// U+00E0 ISOlat1 -->
"aacute", // "á" -- latin small letter a with acute,
// U+00E1 ISOlat1 -->
"acirc", // "â" -- latin small letter a with circumflex,
// U+00E2 ISOlat1 -->
"atilde", // "ã" -- latin small letter a with tilde,
// U+00E3 ISOlat1 -->
"auml", // "ä" -- latin small letter a with diaeresis,
// U+00E4 ISOlat1 -->
"aring", // "å" -- latin small letter a with ring above
// = latin small letter a ring,
// U+00E5 ISOlat1 -->
"aelig", // "æ" -- latin small letter ae
// = latin small ligature ae, U+00E6 ISOlat1 -->
"ccedil", // "ç" -- latin small letter c with cedilla,
// U+00E7 ISOlat1 -->
"egrave", // "è" -- latin small letter e with grave,
// U+00E8 ISOlat1 -->
"eacute", // "é" -- latin small letter e with acute,
// U+00E9 ISOlat1 -->
"ecirc", // "ê" -- latin small letter e with circumflex,
// U+00EA ISOlat1 -->
"euml", // "ë" -- latin small letter e with diaeresis,
// U+00EB ISOlat1 -->
"igrave", // "ì" -- latin small letter i with grave,
// U+00EC ISOlat1 -->
"iacute", // "í" -- latin small letter i with acute,
// U+00ED ISOlat1 -->
"icirc", // "î" -- latin small letter i with circumflex,
// U+00EE ISOlat1 -->
"iuml", // "ï" -- latin small letter i with diaeresis,
// U+00EF ISOlat1 -->
"eth", // "ð" -- latin small letter eth, U+00F0 ISOlat1 -->
"ntilde", // "ñ" -- latin small letter n with tilde,
// U+00F1 ISOlat1 -->
"ograve", // "ò" -- latin small letter o with grave,
// U+00F2 ISOlat1 -->
"oacute", // "ó" -- latin small letter o with acute,
// U+00F3 ISOlat1 -->
"ocirc", // "ô" -- latin small letter o with circumflex,
// U+00F4 ISOlat1 -->
"otilde", // "õ" -- latin small letter o with tilde,
// U+00F5 ISOlat1 -->
"ouml", // "ö" -- latin small letter o with diaeresis,
// U+00F6 ISOlat1 -->
"divide", // "÷" -- division sign, U+00F7 ISOnum -->
"oslash", // "ø" -- latin small letter o with stroke,
// = latin small letter o slash,
// U+00F8 ISOlat1 -->
"ugrave", // "ù" -- latin small letter u with grave,
// U+00F9 ISOlat1 -->
"uacute", // "ú" -- latin small letter u with acute,
// U+00FA ISOlat1 -->
"ucirc", // "û" -- latin small letter u with circumflex,
// U+00FB ISOlat1 -->
"uuml", // "ü" -- latin small letter u with diaeresis,
// U+00FC ISOlat1 -->
"yacute", // "ý" -- latin small letter y with acute,
// U+00FD ISOlat1 -->
"thorn", // "þ" -- latin small letter thorn,
// U+00FE ISOlat1 -->
"yuml" // "ÿ" -- latin small letter y with diaeresis,
// U+00FF ISOlat1 -->
};
}
//
// The contents of this file are subject to the Mozilla Public License Version 1.0 (the "License");
// you may not use this file except in compliance with the License. You may obtain a copy of the
// License at http://www.mozilla.org/MPL/
//
// Software distributed under the License is distributed on an "AS IS" basis,
// WITHOUT WARRANTY OF ANY KIND, either express or implied.
// See the License for the specific language governing rights and limitations under the License.
//
// The Original Code is: all this file.
//
// The Initial Developer of the Original Code is Michael H. Kay.
//
// Portions created by (your name) are Copyright (C) (your legal entity). All Rights Reserved.
//
// Contributor(s): none.
//
© 2015 - 2025 Weber Informatics LLC | Privacy Policy