Hi Daniel,
> Whenever you have the time to
> whittle it down
> to the bare essentials, please post again.
Here is a reduced, standalone test class,
Performance.java.
/*
* Performance.java
*
* Created on 15 October 2001, 22:07
*/
import java.util.* ;
import org.apache.oro.text.regex.* ;
/**
*
* @author jdb
* @version v 1.0
*/
public class Performance {
private static final String
SERVER_ACTIVE_HTML_PATTERN =
/*
* <!-- name="news" -->
* or
* <!-- name="news" template="news-tmpl" -->
*
* (Remember to escape backslash
*
* \n -> \\n
* \w -> \\w
*
* etc)
*
*/
"<!--\\s*name\\s*=\\s*\"([\\w\\-]+)\"\\s*(template\\s*=\\s*\"[\\w\\-]+\")?\\s*-->"
+
/*
* enclosed content
*/
"((\\s|.)*)" +
/*
* <!-- name="/news" -->
*/
"<!--\\s*name\\s*=\\s*\"/\\1\"\\s*-->" ;
static protected PatternMatcher _matcher ;
static protected Pattern _pattern ;
static protected MalformedPatternException
_patternException ;
/* Static initialiser */
{
_matcher = new Perl5Matcher () ;
PatternCompiler compiler = new Perl5Compiler
();
try {
_pattern = compiler.compile (
SERVER_ACTIVE_HTML_PATTERN,
Perl5Compiler.CASE_INSENSITIVE_MASK |
Perl5Compiler.READ_ONLY_MASK );
}
catch(MalformedPatternException e) {
/* how can an exception be thrown from a
static initialiser? */
_pattern = null ;
_patternException = e ;
}
}
/**
* Parse the HTML fragment.
*
* Match comment pairs in psuedo XML format:
*
* <!-- name="xxx" -->
* ...
* <!-- name="/xxx" -->
*
* or
*
* <!-- name="xxx" template="yyy" -->
* ...
* <!-- name="/xxx" -->
*
*
*
*
* @param html The HTML to search in.
*/
protected void matchComments ( String htmlString )
throws Exception {
/* delayed exception from static initialiser
*/
if ( _pattern == null ) {
throw new Exception (
_patternException.toString () );
}
MatchResult result;
PatternMatcherInput input = new
PatternMatcherInput ( htmlString );
int i = 1 ;
boolean matched ;
while( true ) {
long t = System.currentTimeMillis () ;
matched = _matcher.contains (input,
_pattern) ;
System.out.println ( " #" + i +
": " +
( ( System.currentTimeMillis () - t ) /
1000 )
);
if ( ! matched )
break ;
result = _matcher.getMatch ();
i++ ;
}
}
public static void main (String[] args) {
(new Performance ()).match () ;
}
protected void match () {
try {
testBinarySequences () ;
}
catch ( Exception e ) {
e.printStackTrace () ;
}
}
/**
* Test many sequences.
*
* A = the pattern we are looking for
* H = other HTML
*
*/
public void testBinarySequences () throws
Exception {
/*
* (HH = H)
*/
List comboList = Arrays.asList ( new String []
{
/* 1 */
"H", "A",
/* 2 */
"AH", "AA", "HA",
/* 3 */
"AAH", "AAA", "AHA", "HAH", "HAA",
/* 4 */
"AAAH", "AAAA", "AAHA", "AHAH", "AHAA",
"HAAH", "HAAA", "HAHA",
/* 5 */
"AAAAH", "AAAAA", "AAAHA", "AAHAH",
"AAHAA", "AHAAH", "AHAAA", "AHAHA",
"HAAAH", "HAAAA", "HAAHA", "HAHAH",
"HAHAA"
} ) ;
String html = "<b><i>Hi</i></b>\n" ;
String SAHOpen = "<!-- name=\"" ;
String SAHClose = "\" -->" ;
String SAHContent = "<!-- element=\"content\"
-->Hi<!-- element=\"/content\" -->\n";
int namePostfix = 0 ;
Iterator it = comboList.iterator () ;
while ( it.hasNext () ) {
String seq = (String) it.next () ;
StringBuffer sb = new StringBuffer () ;
for ( int i = 0; i < seq.length () ; i++,
namePostfix++ ) {
if ( seq.charAt ( i ) == 'A' ) {
sb.append (
SAHOpen + "name-" + namePostfix +
SAHClose +
SAHContent +
SAHOpen + "/name-" + namePostfix +
SAHClose
) ;
}
else {
sb.append ( html ) ;
}
}
System.out.println ("input: " + seq);
System.out.println ( "(Seconds for each
contains() invocation.)" );
long t = System.currentTimeMillis () ;
matchComments ( sb.toString () ) ;
System.out.println ( "Total seconds: " +
( ( System.currentTimeMillis () - t ) /
1000 )
);
System.out.println ("");
}
}
}
/*
These were the parse times.
(Seconds for each contains() invocation.)
#1: 0
Total seconds: 0
input: A
(Seconds for each contains() invocation.)
#1: 0
#2: 0
Total seconds: 0
input: AH
(Seconds for each contains() invocation.)
#1: 0
#2: 0
Total seconds: 0
input: AA
(Seconds for each contains() invocation.)
#1: 0
#2: 0
#3: 0
Total seconds: 0
input: HA
(Seconds for each contains() invocation.)
#1: 0
#2: 0
Total seconds: 0
input: AAH
(Seconds for each contains() invocation.)
#1: 0
#2: 0
#3: 0
Total seconds: 0
input: AAA
(Seconds for each contains() invocation.)
#1: 13
#2: 0
#3: 0
#4: 0
Total seconds: 13
input: AHA
(Seconds for each contains() invocation.)
#1: 0
#2: 0
#3: 0
Total seconds: 0
input: HAH
(Seconds for each contains() invocation.)
#1: 0
#2: 0
Total seconds: 0
input: HAA
(Seconds for each contains() invocation.)
#1: 0
#2: 0
#3: 0
Total seconds: 0
input: AAAH
(Seconds for each contains() invocation.)
#1: 24
#2: 0
#3: 0
#4: 0
Total seconds: 24
input: AAAA
(Seconds for each contains() invocation.)
--- killed process ---
*/
____________________________________________________________
Do You Yahoo!?
Get your free @yahoo.co.uk address at http://mail.yahoo.co.uk
or your free @yahoo.ie address at http://mail.yahoo.ie
