A sample DOM counter. This sample program illustrates how to
traverse a DOM tree in order to get information about the document.
The output of this program shows the time and count of elements,
attributes, ignorable whitespaces, and characters appearing in
the document. Three times are shown: the parse time, the first
traversal of the document, and the second traversal of the tree.
This class is useful as a "poor-man's" performance tester to
compare the speed and accuracy of various DOM parsers. However,
it is important to note that the first parse time of a parser
will include both VM class load time and parser initialization
that would not be present in subsequent parses with the same
file.
| Field Summary |
|---|
| protected static final String | NAMESPACES_FEATURE_ID | Namespaces feature id (http://xml.org/sax/features/namespaces). |
| protected static final String | VALIDATION_FEATURE_ID | Validation feature id (http://xml.org/sax/features/validation). |
| protected static final String | SCHEMA_VALIDATION_FEATURE_ID | Schema validation feature id (http://apache.org/xml/features/validation/schema). |
| protected static final String | SCHEMA_FULL_CHECKING_FEATURE_ID | Schema full checking feature id (http://apache.org/xml/features/validation/schema-full-checking). |
| protected static final String | HONOUR_ALL_SCHEMA_LOCATIONS_ID | Honour all schema locations feature id (http://apache.org/xml/features/honour-all-schemaLocations). |
| protected static final String | VALIDATE_ANNOTATIONS_ID | Validate schema annotations feature id (http://apache.org/xml/features/validate-annotations). |
| protected static final String | DYNAMIC_VALIDATION_FEATURE_ID | Dynamic validation feature id (http://apache.org/xml/features/validation/dynamic). |
| protected static final String | XINCLUDE_FEATURE_ID | XInclude feature id (http://apache.org/xml/features/xinclude). |
| protected static final String | XINCLUDE_FIXUP_BASE_URIS_FEATURE_ID | XInclude fixup base URIs feature id (http://apache.org/xml/features/xinclude/fixup-base-uris). |
| protected static final String | XINCLUDE_FIXUP_LANGUAGE_FEATURE_ID | XInclude fixup language feature id (http://apache.org/xml/features/xinclude/fixup-language). |
| protected static final String | DEFAULT_PARSER_NAME | Default parser name (dom.wrappers.Xerces). |
| protected static final int | DEFAULT_REPETITION | Default repetition (1). |
| protected static final boolean | DEFAULT_NAMESPACES | Default namespaces support (true). |
| protected static final boolean | DEFAULT_VALIDATION | Default validation support (false). |
| protected static final boolean | DEFAULT_SCHEMA_VALIDATION | Default Schema validation support (false). |
| protected static final boolean | DEFAULT_SCHEMA_FULL_CHECKING | Default Schema full checking support (false). |
| protected static final boolean | DEFAULT_HONOUR_ALL_SCHEMA_LOCATIONS | Default honour all schema locations (false). |
| protected static final boolean | DEFAULT_VALIDATE_ANNOTATIONS | Default validate schema annotations (false). |
| protected static final boolean | DEFAULT_DYNAMIC_VALIDATION | Default dynamic validation support (false). |
| protected static final boolean | DEFAULT_XINCLUDE | Default XInclude processing support (false). |
| protected static final boolean | DEFAULT_XINCLUDE_FIXUP_BASE_URIS | Default XInclude fixup base URIs support (true). |
| protected static final boolean | DEFAULT_XINCLUDE_FIXUP_LANGUAGE | Default XInclude fixup language support (true). |
| protected long | fElements | Number of elements. |
| protected long | fAttributes | Number of attributes. |
| protected long | fCharacters | Number of characters. |
| protected long | fIgnorableWhitespace | Number of ignorable whitespace characters. |
| protected ParserWrapper.DocumentInfo | fDocumentInfo | Document information. |
| Method from dom.Counter Detail: |
|---|
 public void count(Node node) {
// is there anything to do?
if (node == null) {
return;
}
int type = node.getNodeType();
switch (type) {
case Node.DOCUMENT_NODE: {
fElements = 0;
fAttributes = 0;
fCharacters = 0;
fIgnorableWhitespace = 0;
Document document = (Document)node;
count(document.getDocumentElement());
break;
}
case Node.ELEMENT_NODE: {
fElements++;
NamedNodeMap attrs = node.getAttributes();
if (attrs != null) {
fAttributes += attrs.getLength();
}
// drop through to entity reference
}
case Node.ENTITY_REFERENCE_NODE: {
Node child = node.getFirstChild();
while (child != null) {
count(child);
child = child.getNextSibling();
}
break;
}
case Node.CDATA_SECTION_NODE: {
fCharacters += ((Text)node).getLength();
break;
}
case Node.TEXT_NODE: {
if (fDocumentInfo != null) {
Text text = (Text)node;
int length = text.getLength();
if (fDocumentInfo.isIgnorableWhitespace(text)) {
fIgnorableWhitespace += length;
}
else {
fCharacters += length;
}
}
break;
}
}
}
Traverses the specified node, recursively. |
public static void main(String[] argv) {
// is there anything to do?
if (argv.length == 0) {
printUsage();
System.exit(1);
}
// variables
Counter counter = new Counter();
PrintWriter out = new PrintWriter(System.out);
ParserWrapper parser = null;
int repetition = DEFAULT_REPETITION;
boolean namespaces = DEFAULT_NAMESPACES;
boolean validation = DEFAULT_VALIDATION;
boolean schemaValidation = DEFAULT_SCHEMA_VALIDATION;
boolean schemaFullChecking = DEFAULT_SCHEMA_FULL_CHECKING;
boolean honourAllSchemaLocations = DEFAULT_HONOUR_ALL_SCHEMA_LOCATIONS;
boolean validateAnnotations = DEFAULT_VALIDATE_ANNOTATIONS;
boolean dynamicValidation = DEFAULT_DYNAMIC_VALIDATION;
boolean xincludeProcessing = DEFAULT_XINCLUDE;
boolean xincludeFixupBaseURIs = DEFAULT_XINCLUDE_FIXUP_BASE_URIS;
boolean xincludeFixupLanguage = DEFAULT_XINCLUDE_FIXUP_LANGUAGE;
// process arguments
for (int i = 0; i < argv.length; i++) {
String arg = argv[i];
if (arg.startsWith("-")) {
String option = arg.substring(1);
if (option.equals("p")) {
// get parser name
if (++i == argv.length) {
System.err.println("error: Missing argument to -p option.");
}
String parserName = argv[i];
// create parser
try {
parser = (ParserWrapper)Class.forName(parserName).newInstance();
}
catch (Exception e) {
parser = null;
System.err.println("error: Unable to instantiate parser ("+parserName+")");
}
continue;
}
if (option.equals("x")) {
if (++i == argv.length) {
System.err.println("error: Missing argument to -x option.");
continue;
}
String number = argv[i];
try {
int value = Integer.parseInt(number);
if (value < 1) {
System.err.println("error: Repetition must be at least 1.");
continue;
}
repetition = value;
}
catch (NumberFormatException e) {
System.err.println("error: invalid number ("+number+").");
}
continue;
}
if (option.equalsIgnoreCase("n")) {
namespaces = option.equals("n");
continue;
}
if (option.equalsIgnoreCase("v")) {
validation = option.equals("v");
continue;
}
if (option.equalsIgnoreCase("s")) {
schemaValidation = option.equals("s");
continue;
}
if (option.equalsIgnoreCase("f")) {
schemaFullChecking = option.equals("f");
continue;
}
if (option.equalsIgnoreCase("hs")) {
honourAllSchemaLocations = option.equals("hs");
continue;
}
if (option.equalsIgnoreCase("va")) {
validateAnnotations = option.equals("va");
continue;
}
if (option.equalsIgnoreCase("dv")) {
dynamicValidation = option.equals("dv");
continue;
}
if (option.equalsIgnoreCase("xi")) {
xincludeProcessing = option.equals("xi");
continue;
}
if (option.equalsIgnoreCase("xb")) {
xincludeFixupBaseURIs = option.equals("xb");
continue;
}
if (option.equalsIgnoreCase("xl")) {
xincludeFixupLanguage = option.equals("xl");
continue;
}
if (option.equals("h")) {
printUsage();
continue;
}
}
// use default parser?
if (parser == null) {
// create parser
try {
parser = (ParserWrapper)Class.forName(DEFAULT_PARSER_NAME).newInstance();
}
catch (Exception e) {
System.err.println("error: Unable to instantiate parser ("+DEFAULT_PARSER_NAME+")");
continue;
}
}
// set parser features
try {
parser.setFeature(NAMESPACES_FEATURE_ID, namespaces);
}
catch (SAXException e) {
System.err.println("warning: Parser does not support feature ("+NAMESPACES_FEATURE_ID+")");
}
try {
parser.setFeature(VALIDATION_FEATURE_ID, validation);
}
catch (SAXException e) {
System.err.println("warning: Parser does not support feature ("+VALIDATION_FEATURE_ID+")");
}
try {
parser.setFeature(SCHEMA_VALIDATION_FEATURE_ID, schemaValidation);
}
catch (SAXException e) {
System.err.println("warning: Parser does not support feature ("+SCHEMA_VALIDATION_FEATURE_ID+")");
}
try {
parser.setFeature(SCHEMA_FULL_CHECKING_FEATURE_ID, schemaFullChecking);
}
catch (SAXException e) {
System.err.println("warning: Parser does not support feature ("+SCHEMA_FULL_CHECKING_FEATURE_ID+")");
}
try {
parser.setFeature(HONOUR_ALL_SCHEMA_LOCATIONS_ID, honourAllSchemaLocations);
}
catch (SAXException e) {
System.err.println("warning: Parser does not support feature ("+HONOUR_ALL_SCHEMA_LOCATIONS_ID+")");
}
try {
parser.setFeature(VALIDATE_ANNOTATIONS_ID, validateAnnotations);
}
catch (SAXException e) {
System.err.println("warning: Parser does not support feature ("+VALIDATE_ANNOTATIONS_ID+")");
}
try {
parser.setFeature(DYNAMIC_VALIDATION_FEATURE_ID, dynamicValidation);
}
catch (SAXException e) {
System.err.println("warning: Parser does not support feature ("+DYNAMIC_VALIDATION_FEATURE_ID+")");
}
try {
parser.setFeature(XINCLUDE_FEATURE_ID, xincludeProcessing);
}
catch (SAXException e) {
System.err.println("warning: Parser does not support feature ("+XINCLUDE_FEATURE_ID+")");
}
try {
parser.setFeature(XINCLUDE_FIXUP_BASE_URIS_FEATURE_ID, xincludeFixupBaseURIs);
}
catch (SAXException e) {
System.err.println("warning: Parser does not support feature ("+XINCLUDE_FIXUP_BASE_URIS_FEATURE_ID+")");
}
try {
parser.setFeature(XINCLUDE_FIXUP_LANGUAGE_FEATURE_ID, xincludeFixupLanguage);
}
catch (SAXException e) {
System.err.println("warning: Parser does not support feature ("+XINCLUDE_FIXUP_LANGUAGE_FEATURE_ID+")");
}
// parse file
try {
long beforeParse = System.currentTimeMillis();
Document document = null;
for (int j = 0; j < repetition; j++) {
document = parser.parse(arg);
}
long afterParse = System.currentTimeMillis();
long parse = afterParse - beforeParse;
ParserWrapper.DocumentInfo documentInfo = parser.getDocumentInfo();
counter.setDocumentInfo(documentInfo);
long beforeTraverse1 = System.currentTimeMillis();
counter.count(document);
long afterTraverse1 = System.currentTimeMillis();
long traverse1 = afterTraverse1 - beforeTraverse1;
long beforeTraverse2 = System.currentTimeMillis();
counter.count(document);
long afterTraverse2 = System.currentTimeMillis();
long traverse2 = afterTraverse2 - beforeTraverse2;
counter.printResults(out, arg, parse, traverse1, traverse2,
repetition);
}
catch (SAXParseException e) {
// ignore
}
catch (Exception e) {
System.err.println("error: Parse error occurred - "+e.getMessage());
Exception se = e;
if (e instanceof SAXException) {
se = ((SAXException)e).getException();
}
if (se != null)
se.printStackTrace(System.err);
else
e.printStackTrace(System.err);
}
}
} Main program entry point. |
public void printResults(PrintWriter out,
String uri,
long parse,
long traverse1,
long traverse2,
int repetition) {
// filename.xml: 631/200/100 ms (4 elems, 0 attrs, 78 spaces, 0 chars)
out.print(uri);
out.print(": ");
if (repetition == 1) {
out.print(parse);
}
else {
out.print(parse);
out.print('/");
out.print(repetition);
out.print('=");
out.print(parse/repetition);
}
out.print(';");
out.print(traverse1);
out.print(';");
out.print(traverse2);
out.print(" ms (");
out.print(fElements);
out.print(" elems, ");
out.print(fAttributes);
out.print(" attrs, ");
out.print(fIgnorableWhitespace);
out.print(" spaces, ");
out.print(fCharacters);
out.print(" chars)");
out.println();
out.flush();
} |
public void setDocumentInfo(ParserWrapper.DocumentInfo documentInfo) {
//
// Public methods
//
fDocumentInfo = documentInfo;
} |
dom.Counter