Re: Most efficient character parsing.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: Most efficient character parsing.

Subject: Re: Most efficient character parsing.
From: email@hidden
Date: Thu, 23 Feb 2006 23:16:30 -0500

Okay, I took the advice given about the test I ran, modified it and ran it again tonight.

Here is a summary of the test and the files I used to test are located at the bottom incase you want to validate my findings.

I created two direct actions. One that uses a boolean array map and one that uses a regular _expression_ to strip invalid ISO 8859-1 characters. This time I used a much larger string for the test. I also compiled the pattern in the contructor of Regex style object to that pattern compiling only happens once per test. Each test ran the string through the parser 10,000 times. I rebuilt the application prior to every test that was run.

Here are the results:

Boolean Array Map (in milliseconds)

9589

9517

9809

9570

9674

9558

9460

9704

9629

10051

Regex ( in milliseconds)

28915

28281

28218

29444

37207

29006

29019

28908

28813

28907

Looks like the array map was 3 times more efficient.

Here are the files I created for the test.

DirectAction.java

-----------------------

// DirectAction.java

// Project Norway

// Created by ericstewart on 2/15/06

import com.webobjects.foundation.*;

import com.webobjects.appserver.*;

import com.webobjects.appserver.xml.*;

import com.webobjects.eocontrol.*;

import java.util.*;

public class DirectAction extends WODirectAction {

public DirectAction(WORequest aRequest) {

super(aRequest);

}

public WOActionResults defaultAction() {

return pageWithName("Main");

}

public WOActionResults charSpeedArrayMapAction() {

// build test string

StringBuffer testString = new StringBuffer("kfdlas;n 0wqm dsagjnoisa fd;af[aghjr3q-tifnewna fafjpewiq nor0dafnlw;l jfh0w flw;f saofh8");

testString.append((char)1000);

testString.append("fd0 f023 fkdls anflrwjap fsa[w fjnw f[2- dawjv094 tn3oh9k04r3 309r3hg854mvrm3w0v5nw[0 v9");

testString.append("qmgn vjdsop 00 89w nv3ni0vr nmv p3orm vnrv rm v fw mdndw sjuio490n v uckm4uv4n fj iivkmcj");

testString.append("o489jnrbnv8m 5tjvb6fci9 uv77vj vu v7v 678i9ls fdgo09 i9 r98 jk f78 fm,f juy fiker fdmf");

testString.append((char)10000);

testString.append("irmvn 984mn juf78 km 4 d0v76 7 m j37 67k 6mbvjk8cv56 6yjn r vcjv u7849md cx;df]c0-8 end");

testString.append("4mvj930 fn89 2 no98304 nr0mj v8v87395 09vm vwlr e ;vd s,mnrv K VUYRMNVDHJ SUISVI DVO$MMV");

testString.append("i4m *$N lfju67 K$(N kjgurn jkd7 KMN* JND^&V kf9]6l4m,d id 8f4 j md k3idd8j4m cems duij4m");

testString.append((char)100000);

testString.append("imn4nf8 IUj4nvjud8mner iec 883mnd J893M K VEniw8923m mdwjw8m vmskl w o290894 vw m s s94");

testString.append("fwjo wo fro3neqwvr03 f94fdwc J VW)RJ)VJ EQW( VNDSHVV@HPNVDSOPV)J*(J V)W)RHjiwo vhjdwj vlj");

testString.append("fwonnf 02f0 nesa0fe23q0cwajnv fj f jwjv jdwoav0ds a9=dsa j dsaj0 vdwavs00nv r3 j3jvr0j vj");

testString.append((char)1000000);

testString.append("jfdlas 0i0 0)) JN(HD J CHDH kdsa 30 nrvmnds 90 ) JNC(h0wejvj-r3j dns huvj0rje 0-fj v3jnv");

testString.append("0230m w0ondnw n003n n vd93n vds nah 39nsnv l;vMVOP MNVNVNV NO NDN LVN H JKJOPW_ ()_U*( 8");

testString.append("jfu39 in jvsa 803i njfwe u03 hu9n iv3ni-ih8v jvi99 0h rh nine-JMIW)IJ ERNM VR ()V) VW V(");

testString.append((char)10000000);

testString.append("8jkn4n u7854iujK&&MR jfb7bf6j JEF7VR374KFB MNHJUEF KLI88 AMC898 WJ0 E MNMNP, W0E89898Zj");

testString.append("oo9ij v 930 N(DNJ80 390n vu989*^%R@#$() vmknv98u&*^&& vnsjkv sg o78h 9nN H(RHnir nov ew8");

testString.append("mmn vrn9 8 NN Jn 9uh70 e4hnbno v nu9vb7ev uh9n4njNJU( H&*( V)H* CNIn uve3u 089dn 9dmn3 90");

testString.append((char)10000);

testString.append("0-,rfvk9c 8v rjnn Su h9r43h90 r30i j nmvdsnj cu h90eh83ij0 vniinodh9 8g7r37 h vdj huvds g");

testString.append("0f3 9in vn H&A nifmnk no JvA H*(j8 h3j jieh89 rvh8 -34 j[v nd diuvzh 89vreh vj9v0j89w v");

testString.append("9034 jN( AF#NU(nOP JWhj0je v 9j 0 [J) j 0verj gj089mefi iv9ni ji jv3j 0vj0j bj 80 bj8 vj");

testString.append((char)100000);

testString.append("030kmc 8j7896 nNYG&*&*GH nvr3invfrh9vr34j8hn H* H*( h89 43jhj8 sh737u095 vnhv uherj9wj9");

testString.append("903nmdvnhu98wehjr3ndfh8 we9n ufe78 hv54u9 wm njn a 8h h8fj9 vh89h 89 H* )J*vj0 3j09 j mew");

testString.append("09 vmhij jve3i vn wv h vsh v kln;ms p[]hij 8y 9ty7h u5 jnvkln ;v Shj8 u8-u59 0gj vu8 jkrj");

testString.append((char)1000000);

testString.append("NUIO*(n v3r i00)(**(j 3 u()&T^ewju jkbdj v89h j rmnJI HJ Ijiv rj948jv bih vjvrjvvjvrjhve");

testString.append("9498 vnm v93j89r439j0fj nvjj3rjjvr3j90 vj9 j5mpbejsvh8bw4kop5jinovjv3j 9v0j93vj 09v35j 0v");

testString.append("m,fi0nr n jvjn vj8j0-9 j35 i5jijv er hjvsj v j99 3-g5 verj ivj9 v rj9 g4ov zswjvr3i jfKJ ");

testString.append((char)1000);

testString.append("fd0 f023 fkdls anflrwjap fsa[w fjnw f[2- dawjv094 tn3oh9k04r3 309r3hg854mvrm3w0v5nw[0 v9");

testString.append("qmgn vjdsop 00 89w nv3ni0vr nmv p3orm vnrv rm v fw mdndw sjuio490n v uckm4uv4n fj iivkmcj");

testString.append("o489jnrbnv8m 5tjvb6fci9 uv77vj vu v7v 678i9ls fdgo09 i9 r98 jk f78 fm,f juy fiker fdmf");

testString.append((char)10000);

testString.append("irmvn 984mn juf78 km 4 d0v76 7 m j37 67k 6mbvjk8cv56 6yjn r vcjv u7849md cx;df]c0-8 end");

testString.append("4mvj930 fn89 2 no98304 nr0mj v8v87395 09vm vwlr e ;vd s,mnrv K VUYRMNVDHJ SUISVI DVO$MMV");

testString.append("i4m *$N lfju67 K$(N kjgurn jkd7 KMN* JND^&V kf9]6l4m,d id 8f4 j md k3idd8j4m cems duij4m");

testString.append((char)100000);

testString.append("imn4nf8 IUj4nvjud8mner iec 883mnd J893M K VEniw8923m mdwjw8m vmskl w o290894 vw m s s94");

testString.append("fwjo wo fro3neqwvr03 f94fdwc J VW)RJ)VJ EQW( VNDSHVV@HPNVDSOPV)J*(J V)W)RHjiwo vhjdwj vlj");

testString.append("fwonnf 02f0 nesa0fe23q0cwajnv fj f jwjv jdwoav0ds a9=dsa j dsaj0 vdwavs00nv r3 j3jvr0j vj");

testString.append((char)1000000);

testString.append("jfdlas 0i0 0)) JN(HD J CHDH kdsa 30 nrvmnds 90 ) JNC(h0wejvj-r3j dns huvj0rje 0-fj v3jnv");

testString.append("0230m w0ondnw n003n n vd93n vds nah 39nsnv l;vMVOP MNVNVNV NO NDN LVN H JKJOPW_ ()_U*( 8");

testString.append("jfu39 in jvsa 803i njfwe u03 hu9n iv3ni-ih8v jvi99 0h rh nine-JMIW)IJ ERNM VR ()V) VW V(");

testString.append((char)10000000);

testString.append("8jkn4n u7854iujK&&MR jfb7bf6j JEF7VR374KFB MNHJUEF KLI88 AMC898 WJ0 E MNMNP, W0E89898Zj");

testString.append("oo9ij v 930 N(DNJ80 390n vu989*^%R@#$() vmknv98u&*^&& vnsjkv sg o78h 9nN H(RHnir nov ew8");

testString.append("mmn vrn9 8 NN Jn 9uh70 e4hnbno v nu9vb7ev uh9n4njNJU( H&*( V)H* CNIn uve3u 089dn 9dmn3 90");

testString.append((char)10000);

testString.append("0-,rfvk9c 8v rjnn Su h9r43h90 r30i j nmvdsnj cu h90eh83ij0 vniinodh9 8g7r37 h vdj huvds g");

testString.append("0f3 9in vn H&A nifmnk no JvA H*(j8 h3j jieh89 rvh8 -34 j[v nd diuvzh 89vreh vj9v0j89w v");

testString.append("9034 jN( AF#NU(nOP JWhj0je v 9j 0 [J) j 0verj gj089mefi iv9ni ji jv3j 0vj0j bj 80 bj8 vj");

testString.append((char)100000);

testString.append("030kmc 8j7896 nNYG&*&*GH nvr3invfrh9vr34j8hn H* H*( h89 43jhj8 sh737u095 vnhv uherj9wj9");

testString.append("903nmdvnhu98wehjr3ndfh8 we9n ufe78 hv54u9 wm njn a 8h h8fj9 vh89h 89 H* )J*vj0 3j09 j mew");

testString.append("09 vmhij jve3i vn wv h vsh v kln;ms p[]hij 8y 9ty7h u5 jnvkln ;v Shj8 u8-u59 0gj vu8 jkrj");

testString.append((char)1000000);

testString.append("NUIO*(n v3r i00)(**(j 3 u()&T^ewju jkbdj v89h j rmnJI HJ Ijiv rj948jv bih vjvrjvvjvrjhve");

testString.append("9498 vnm v93j89r439j0fj nvjj3rjjvr3j90 vj9 j5mpbejsvh8bw4kop5jinovjv3j 9v0j93vj 09v35j 0v");

testString.append("m,fi0nr n jvjn vj8j0-9 j35 i5jijv er hjvsj v j99 3-g5 verj ivj9 v rj9 g4ov zswjvr3i jfKJ ");

testString.append((char)1000);

testString.append("fd0 f023 fkdls anflrwjap fsa[w fjnw f[2- dawjv094 tn3oh9k04r3 309r3hg854mvrm3w0v5nw[0 v9");

testString.append("qmgn vjdsop 00 89w nv3ni0vr nmv p3orm vnrv rm v fw mdndw sjuio490n v uckm4uv4n fj iivkmcj");

testString.append("o489jnrbnv8m 5tjvb6fci9 uv77vj vu v7v 678i9ls fdgo09 i9 r98 jk f78 fm,f juy fiker fdmf");

testString.append((char)10000);

testString.append("irmvn 984mn juf78 km 4 d0v76 7 m j37 67k 6mbvjk8cv56 6yjn r vcjv u7849md cx;df]c0-8 end");

testString.append("4mvj930 fn89 2 no98304 nr0mj v8v87395 09vm vwlr e ;vd s,mnrv K VUYRMNVDHJ SUISVI DVO$MMV");

testString.append("i4m *$N lfju67 K$(N kjgurn jkd7 KMN* JND^&V kf9]6l4m,d id 8f4 j md k3idd8j4m cems duij4m");

testString.append((char)100000);

testString.append("imn4nf8 IUj4nvjud8mner iec 883mnd J893M K VEniw8923m mdwjw8m vmskl w o290894 vw m s s94");

testString.append("fwjo wo fro3neqwvr03 f94fdwc J VW)RJ)VJ EQW( VNDSHVV@HPNVDSOPV)J*(J V)W)RHjiwo vhjdwj vlj");

testString.append("fwonnf 02f0 nesa0fe23q0cwajnv fj f jwjv jdwoav0ds a9=dsa j dsaj0 vdwavs00nv r3 j3jvr0j vj");

testString.append((char)1000000);

testString.append("jfdlas 0i0 0)) JN(HD J CHDH kdsa 30 nrvmnds 90 ) JNC(h0wejvj-r3j dns huvj0rje 0-fj v3jnv");

testString.append("0230m w0ondnw n003n n vd93n vds nah 39nsnv l;vMVOP MNVNVNV NO NDN LVN H JKJOPW_ ()_U*( 8");

testString.append("jfu39 in jvsa 803i njfwe u03 hu9n iv3ni-ih8v jvi99 0h rh nine-JMIW)IJ ERNM VR ()V) VW V(");

testString.append((char)10000000);

testString.append("8jkn4n u7854iujK&&MR jfb7bf6j JEF7VR374KFB MNHJUEF KLI88 AMC898 WJ0 E MNMNP, W0E89898Zj");

testString.append("oo9ij v 930 N(DNJ80 390n vu989*^%R@#$() vmknv98u&*^&& vnsjkv sg o78h 9nN H(RHnir nov ew8");

testString.append("mmn vrn9 8 NN Jn 9uh70 e4hnbno v nu9vb7ev uh9n4njNJU( H&*( V)H* CNIn uve3u 089dn 9dmn3 90");

testString.append((char)10000);

testString.append("0-,rfvk9c 8v rjnn Su h9r43h90 r30i j nmvdsnj cu h90eh83ij0 vniinodh9 8g7r37 h vdj huvds g");

testString.append("0f3 9in vn H&A nifmnk no JvA H*(j8 h3j jieh89 rvh8 -34 j[v nd diuvzh 89vreh vj9v0j89w v");

testString.append("9034 jN( AF#NU(nOP JWhj0je v 9j 0 [J) j 0verj gj089mefi iv9ni ji jv3j 0vj0j bj 80 bj8 vj");

testString.append((char)100000);

testString.append("030kmc 8j7896 nNYG&*&*GH nvr3invfrh9vr34j8hn H* H*( h89 43jhj8 sh737u095 vnhv uherj9wj9");

testString.append("903nmdvnhu98wehjr3ndfh8 we9n ufe78 hv54u9 wm njn a 8h h8fj9 vh89h 89 H* )J*vj0 3j09 j mew");

testString.append("09 vmhij jve3i vn wv h vsh v kln;ms p[]hij 8y 9ty7h u5 jnvkln ;v Shj8 u8-u59 0gj vu8 jkrj");

testString.append((char)1000000);

testString.append("NUIO*(n v3r i00)(**(j 3 u()&T^ewju jkbdj v89h j rmnJI HJ Ijiv rj948jv bih vjvrjvvjvrjhve");

testString.append("9498 vnm v93j89r439j0fj nvjj3rjjvr3j90 vj9 j5mpbejsvh8bw4kop5jinovjv3j 9v0j93vj 09v35j 0v");

testString.append("m,fi0nr n jvjn vj8j0-9 j35 i5jijv er hjvsj v j99 3-g5 verj ivj9 v rj9 g4ov zswjvr3i jfKJ ");

// Strip illegal characters.

NSTimestamp time1 = new NSTimestamp();

ISOLatin1CharacterUtility charUtility = new ISOLatin1CharacterUtility();

String resultString = "";

for(int i = 0; i < 10000; i++) {

resultString = charUtility.stripInvalidCharsFromString(testString.toString());

}

NSTimestamp time2 = new NSTimestamp();

GregorianCalendar startCal = new GregorianCalendar();

GregorianCalendar endCal = new GregorianCalendar();

long diffMillis = 0;

startCal.setTime(time1);

endCal.setTime(time2);

diffMillis = endCal.getTimeInMillis() - startCal.getTimeInMillis();

NSLog.debug.appendln("Array map time to parse string: "+diffMillis);

Main page = (Main)pageWithName("Main");

return page;

}

public WOActionResults charSpeedRegexAction() {

// build test string

StringBuffer testString = new StringBuffer("kfdlas;n 0wqm dsagjnoisa fd;af[aghjr3q-tifnewna fafjpewiq nor0dafnlw;l jfh0w flw;f saofh8");

testString.append((char)1000);

testString.append("fd0 f023 fkdls anflrwjap fsa[w fjnw f[2- dawjv094 tn3oh9k04r3 309r3hg854mvrm3w0v5nw[0 v9");

testString.append("qmgn vjdsop 00 89w nv3ni0vr nmv p3orm vnrv rm v fw mdndw sjuio490n v uckm4uv4n fj iivkmcj");

testString.append("o489jnrbnv8m 5tjvb6fci9 uv77vj vu v7v 678i9ls fdgo09 i9 r98 jk f78 fm,f juy fiker fdmf");

testString.append((char)10000);

testString.append("irmvn 984mn juf78 km 4 d0v76 7 m j37 67k 6mbvjk8cv56 6yjn r vcjv u7849md cx;df]c0-8 end");

testString.append("4mvj930 fn89 2 no98304 nr0mj v8v87395 09vm vwlr e ;vd s,mnrv K VUYRMNVDHJ SUISVI DVO$MMV");

testString.append("i4m *$N lfju67 K$(N kjgurn jkd7 KMN* JND^&V kf9]6l4m,d id 8f4 j md k3idd8j4m cems duij4m");

testString.append((char)100000);

testString.append("imn4nf8 IUj4nvjud8mner iec 883mnd J893M K VEniw8923m mdwjw8m vmskl w o290894 vw m s s94");

testString.append("fwjo wo fro3neqwvr03 f94fdwc J VW)RJ)VJ EQW( VNDSHVV@HPNVDSOPV)J*(J V)W)RHjiwo vhjdwj vlj");

testString.append("fwonnf 02f0 nesa0fe23q0cwajnv fj f jwjv jdwoav0ds a9=dsa j dsaj0 vdwavs00nv r3 j3jvr0j vj");

testString.append((char)1000000);

testString.append("jfdlas 0i0 0)) JN(HD J CHDH kdsa 30 nrvmnds 90 ) JNC(h0wejvj-r3j dns huvj0rje 0-fj v3jnv");

testString.append("0230m w0ondnw n003n n vd93n vds nah 39nsnv l;vMVOP MNVNVNV NO NDN LVN H JKJOPW_ ()_U*( 8");

testString.append("jfu39 in jvsa 803i njfwe u03 hu9n iv3ni-ih8v jvi99 0h rh nine-JMIW)IJ ERNM VR ()V) VW V(");

testString.append((char)10000000);

testString.append("8jkn4n u7854iujK&&MR jfb7bf6j JEF7VR374KFB MNHJUEF KLI88 AMC898 WJ0 E MNMNP, W0E89898Zj");

testString.append("oo9ij v 930 N(DNJ80 390n vu989*^%R@#$() vmknv98u&*^&& vnsjkv sg o78h 9nN H(RHnir nov ew8");

testString.append("mmn vrn9 8 NN Jn 9uh70 e4hnbno v nu9vb7ev uh9n4njNJU( H&*( V)H* CNIn uve3u 089dn 9dmn3 90");

testString.append((char)10000);

testString.append("0-,rfvk9c 8v rjnn Su h9r43h90 r30i j nmvdsnj cu h90eh83ij0 vniinodh9 8g7r37 h vdj huvds g");

testString.append("0f3 9in vn H&A nifmnk no JvA H*(j8 h3j jieh89 rvh8 -34 j[v nd diuvzh 89vreh vj9v0j89w v");

testString.append("9034 jN( AF#NU(nOP JWhj0je v 9j 0 [J) j 0verj gj089mefi iv9ni ji jv3j 0vj0j bj 80 bj8 vj");

testString.append((char)100000);

testString.append("030kmc 8j7896 nNYG&*&*GH nvr3invfrh9vr34j8hn H* H*( h89 43jhj8 sh737u095 vnhv uherj9wj9");

testString.append("903nmdvnhu98wehjr3ndfh8 we9n ufe78 hv54u9 wm njn a 8h h8fj9 vh89h 89 H* )J*vj0 3j09 j mew");

testString.append("09 vmhij jve3i vn wv h vsh v kln;ms p[]hij 8y 9ty7h u5 jnvkln ;v Shj8 u8-u59 0gj vu8 jkrj");

testString.append((char)1000000);

testString.append("NUIO*(n v3r i00)(**(j 3 u()&T^ewju jkbdj v89h j rmnJI HJ Ijiv rj948jv bih vjvrjvvjvrjhve");

testString.append("9498 vnm v93j89r439j0fj nvjj3rjjvr3j90 vj9 j5mpbejsvh8bw4kop5jinovjv3j 9v0j93vj 09v35j 0v");

testString.append("m,fi0nr n jvjn vj8j0-9 j35 i5jijv er hjvsj v j99 3-g5 verj ivj9 v rj9 g4ov zswjvr3i jfKJ ");

testString.append((char)1000);

testString.append("fd0 f023 fkdls anflrwjap fsa[w fjnw f[2- dawjv094 tn3oh9k04r3 309r3hg854mvrm3w0v5nw[0 v9");

testString.append("qmgn vjdsop 00 89w nv3ni0vr nmv p3orm vnrv rm v fw mdndw sjuio490n v uckm4uv4n fj iivkmcj");

testString.append("o489jnrbnv8m 5tjvb6fci9 uv77vj vu v7v 678i9ls fdgo09 i9 r98 jk f78 fm,f juy fiker fdmf");

testString.append((char)10000);

testString.append("irmvn 984mn juf78 km 4 d0v76 7 m j37 67k 6mbvjk8cv56 6yjn r vcjv u7849md cx;df]c0-8 end");

testString.append("4mvj930 fn89 2 no98304 nr0mj v8v87395 09vm vwlr e ;vd s,mnrv K VUYRMNVDHJ SUISVI DVO$MMV");

testString.append("i4m *$N lfju67 K$(N kjgurn jkd7 KMN* JND^&V kf9]6l4m,d id 8f4 j md k3idd8j4m cems duij4m");

testString.append((char)100000);

testString.append("imn4nf8 IUj4nvjud8mner iec 883mnd J893M K VEniw8923m mdwjw8m vmskl w o290894 vw m s s94");

testString.append("fwjo wo fro3neqwvr03 f94fdwc J VW)RJ)VJ EQW( VNDSHVV@HPNVDSOPV)J*(J V)W)RHjiwo vhjdwj vlj");

testString.append("fwonnf 02f0 nesa0fe23q0cwajnv fj f jwjv jdwoav0ds a9=dsa j dsaj0 vdwavs00nv r3 j3jvr0j vj");

testString.append((char)1000000);

testString.append("jfdlas 0i0 0)) JN(HD J CHDH kdsa 30 nrvmnds 90 ) JNC(h0wejvj-r3j dns huvj0rje 0-fj v3jnv");

testString.append("0230m w0ondnw n003n n vd93n vds nah 39nsnv l;vMVOP MNVNVNV NO NDN LVN H JKJOPW_ ()_U*( 8");

testString.append("jfu39 in jvsa 803i njfwe u03 hu9n iv3ni-ih8v jvi99 0h rh nine-JMIW)IJ ERNM VR ()V) VW V(");

testString.append((char)10000000);

testString.append("8jkn4n u7854iujK&&MR jfb7bf6j JEF7VR374KFB MNHJUEF KLI88 AMC898 WJ0 E MNMNP, W0E89898Zj");

testString.append("oo9ij v 930 N(DNJ80 390n vu989*^%R@#$() vmknv98u&*^&& vnsjkv sg o78h 9nN H(RHnir nov ew8");

testString.append("mmn vrn9 8 NN Jn 9uh70 e4hnbno v nu9vb7ev uh9n4njNJU( H&*( V)H* CNIn uve3u 089dn 9dmn3 90");

testString.append((char)10000);

testString.append("0-,rfvk9c 8v rjnn Su h9r43h90 r30i j nmvdsnj cu h90eh83ij0 vniinodh9 8g7r37 h vdj huvds g");

testString.append("0f3 9in vn H&A nifmnk no JvA H*(j8 h3j jieh89 rvh8 -34 j[v nd diuvzh 89vreh vj9v0j89w v");

testString.append("9034 jN( AF#NU(nOP JWhj0je v 9j 0 [J) j 0verj gj089mefi iv9ni ji jv3j 0vj0j bj 80 bj8 vj");

testString.append((char)100000);

testString.append("030kmc 8j7896 nNYG&*&*GH nvr3invfrh9vr34j8hn H* H*( h89 43jhj8 sh737u095 vnhv uherj9wj9");

testString.append("903nmdvnhu98wehjr3ndfh8 we9n ufe78 hv54u9 wm njn a 8h h8fj9 vh89h 89 H* )J*vj0 3j09 j mew");

testString.append("09 vmhij jve3i vn wv h vsh v kln;ms p[]hij 8y 9ty7h u5 jnvkln ;v Shj8 u8-u59 0gj vu8 jkrj");

testString.append((char)1000000);

testString.append("NUIO*(n v3r i00)(**(j 3 u()&T^ewju jkbdj v89h j rmnJI HJ Ijiv rj948jv bih vjvrjvvjvrjhve");

testString.append("9498 vnm v93j89r439j0fj nvjj3rjjvr3j90 vj9 j5mpbejsvh8bw4kop5jinovjv3j 9v0j93vj 09v35j 0v");

testString.append("m,fi0nr n jvjn vj8j0-9 j35 i5jijv er hjvsj v j99 3-g5 verj ivj9 v rj9 g4ov zswjvr3i jfKJ ");

testString.append((char)1000);

testString.append("fd0 f023 fkdls anflrwjap fsa[w fjnw f[2- dawjv094 tn3oh9k04r3 309r3hg854mvrm3w0v5nw[0 v9");

testString.append("qmgn vjdsop 00 89w nv3ni0vr nmv p3orm vnrv rm v fw mdndw sjuio490n v uckm4uv4n fj iivkmcj");

testString.append("o489jnrbnv8m 5tjvb6fci9 uv77vj vu v7v 678i9ls fdgo09 i9 r98 jk f78 fm,f juy fiker fdmf");

testString.append((char)10000);

testString.append("irmvn 984mn juf78 km 4 d0v76 7 m j37 67k 6mbvjk8cv56 6yjn r vcjv u7849md cx;df]c0-8 end");

testString.append("4mvj930 fn89 2 no98304 nr0mj v8v87395 09vm vwlr e ;vd s,mnrv K VUYRMNVDHJ SUISVI DVO$MMV");

testString.append("i4m *$N lfju67 K$(N kjgurn jkd7 KMN* JND^&V kf9]6l4m,d id 8f4 j md k3idd8j4m cems duij4m");

testString.append((char)100000);

testString.append("imn4nf8 IUj4nvjud8mner iec 883mnd J893M K VEniw8923m mdwjw8m vmskl w o290894 vw m s s94");

testString.append("fwjo wo fro3neqwvr03 f94fdwc J VW)RJ)VJ EQW( VNDSHVV@HPNVDSOPV)J*(J V)W)RHjiwo vhjdwj vlj");

testString.append("fwonnf 02f0 nesa0fe23q0cwajnv fj f jwjv jdwoav0ds a9=dsa j dsaj0 vdwavs00nv r3 j3jvr0j vj");

testString.append((char)1000000);

testString.append("jfdlas 0i0 0)) JN(HD J CHDH kdsa 30 nrvmnds 90 ) JNC(h0wejvj-r3j dns huvj0rje 0-fj v3jnv");

testString.append("0230m w0ondnw n003n n vd93n vds nah 39nsnv l;vMVOP MNVNVNV NO NDN LVN H JKJOPW_ ()_U*( 8");

testString.append("jfu39 in jvsa 803i njfwe u03 hu9n iv3ni-ih8v jvi99 0h rh nine-JMIW)IJ ERNM VR ()V) VW V(");

testString.append((char)10000000);

testString.append("8jkn4n u7854iujK&&MR jfb7bf6j JEF7VR374KFB MNHJUEF KLI88 AMC898 WJ0 E MNMNP, W0E89898Zj");

testString.append("oo9ij v 930 N(DNJ80 390n vu989*^%R@#$() vmknv98u&*^&& vnsjkv sg o78h 9nN H(RHnir nov ew8");

testString.append("mmn vrn9 8 NN Jn 9uh70 e4hnbno v nu9vb7ev uh9n4njNJU( H&*( V)H* CNIn uve3u 089dn 9dmn3 90");

testString.append((char)10000);

testString.append("0-,rfvk9c 8v rjnn Su h9r43h90 r30i j nmvdsnj cu h90eh83ij0 vniinodh9 8g7r37 h vdj huvds g");

testString.append("0f3 9in vn H&A nifmnk no JvA H*(j8 h3j jieh89 rvh8 -34 j[v nd diuvzh 89vreh vj9v0j89w v");

testString.append("9034 jN( AF#NU(nOP JWhj0je v 9j 0 [J) j 0verj gj089mefi iv9ni ji jv3j 0vj0j bj 80 bj8 vj");

testString.append((char)100000);

testString.append("030kmc 8j7896 nNYG&*&*GH nvr3invfrh9vr34j8hn H* H*( h89 43jhj8 sh737u095 vnhv uherj9wj9");

testString.append("903nmdvnhu98wehjr3ndfh8 we9n ufe78 hv54u9 wm njn a 8h h8fj9 vh89h 89 H* )J*vj0 3j09 j mew");

testString.append("09 vmhij jve3i vn wv h vsh v kln;ms p[]hij 8y 9ty7h u5 jnvkln ;v Shj8 u8-u59 0gj vu8 jkrj");

testString.append((char)1000000);

testString.append("NUIO*(n v3r i00)(**(j 3 u()&T^ewju jkbdj v89h j rmnJI HJ Ijiv rj948jv bih vjvrjvvjvrjhve");

testString.append("9498 vnm v93j89r439j0fj nvjj3rjjvr3j90 vj9 j5mpbejsvh8bw4kop5jinovjv3j 9v0j93vj 09v35j 0v");

testString.append("m,fi0nr n jvjn vj8j0-9 j35 i5jijv er hjvsj v j99 3-g5 verj ivj9 v rj9 g4ov zswjvr3i jfKJ ");

// Strip illegal characters.

NSTimestamp time1 = new NSTimestamp();

ISOLatin1CharacterUtilityRegex charUtility = new ISOLatin1CharacterUtilityRegex();

String resultString = "";

for(int i = 0; i < 10000; i++) {

resultString = charUtility.stripInvalidCharsFromString(testString.toString());

}

NSTimestamp time2 = new NSTimestamp();

GregorianCalendar startCal = new GregorianCalendar();

GregorianCalendar endCal = new GregorianCalendar();

long diffMillis = 0;

startCal.setTime(time1);

endCal.setTime(time2);

diffMillis = endCal.getTimeInMillis() - startCal.getTimeInMillis();

NSLog.debug.appendln("Regex time to parse string: "+diffMillis);

Main page = (Main)pageWithName("Main");

return page;

}

ArrayMap Solution

-------------------------

// ISOLatin1CharacterUtilityArrayMap.java

// Norway

// Created by Eric Stewart on 2/19/06.

public class ISOLatin1CharacterUtility {

private boolean[] charMap = new boolean[256];

public ISOLatin1CharacterUtility() {

// Initialize ISO-8859-1 character map.

charMap[9] = true; charMap[10] = true; charMap[13] = true; charMap[32] = true;

charMap[33] = true; charMap[34] = true; charMap[35] = true; charMap[36] = true;

charMap[37] = true; charMap[38] = true; charMap[39] = true; charMap[40] = true;

charMap[41] = true; charMap[42] = true; charMap[43] = true; charMap[44] = true;

charMap[45] = true; charMap[46] = true; charMap[47] = true; charMap[48] = true;

charMap[49] = true; charMap[50] = true; charMap[51] = true; charMap[52] = true;

charMap[53] = true; charMap[54] = true; charMap[55] = true; charMap[56] = true;

charMap[57] = true; charMap[58] = true; charMap[59] = true; charMap[60] = true;

charMap[61] = true; charMap[62] = true; charMap[63] = true; charMap[64] = true;

charMap[65] = true; charMap[66] = true; charMap[67] = true; charMap[68] = true;

charMap[69] = true; charMap[70] = true; charMap[71] = true; charMap[72] = true;

charMap[73] = true; charMap[74] = true; charMap[75] = true; charMap[76] = true;

charMap[77] = true; charMap[78] = true; charMap[79] = true; charMap[80] = true;

charMap[81] = true; charMap[82] = true; charMap[83] = true; charMap[84] = true;

charMap[85] = true; charMap[86] = true; charMap[87] = true; charMap[88] = true;

charMap[89] = true; charMap[90] = true; charMap[91] = true; charMap[92] = true;

charMap[93] = true; charMap[94] = true; charMap[95] = true; charMap[96] = true;

charMap[97] = true; charMap[98] = true; charMap[99] = true; charMap[100] = true;

charMap[101] = true; charMap[102] = true; charMap[103] = true; charMap[104] = true;

charMap[105] = true; charMap[106] = true; charMap[107] = true; charMap[108] = true;

charMap[109] = true; charMap[110] = true; charMap[111] = true; charMap[112] = true;

charMap[113] = true; charMap[114] = true; charMap[115] = true; charMap[116] = true;

charMap[117] = true; charMap[118] = true; charMap[119] = true; charMap[120] = true;

charMap[121] = true; charMap[122] = true; charMap[123] = true; charMap[124] = true;

charMap[125] = true; charMap[126] = true; charMap[160] = true; charMap[161] = true;

charMap[162] = true; charMap[163] = true; charMap[164] = true; charMap[165] = true;

charMap[166] = true; charMap[167] = true; charMap[168] = true; charMap[169] = true;

charMap[170] = true; charMap[171] = true; charMap[172] = true; charMap[173] = true;

charMap[174] = true; charMap[175] = true; charMap[176] = true; charMap[177] = true;

charMap[178] = true; charMap[179] = true; charMap[180] = true; charMap[181] = true;

charMap[182] = true; charMap[183] = true; charMap[184] = true; charMap[185] = true;

charMap[186] = true; charMap[187] = true; charMap[188] = true; charMap[189] = true;

charMap[190] = true; charMap[191] = true; charMap[192] = true; charMap[193] = true;

charMap[194] = true; charMap[195] = true; charMap[196] = true; charMap[197] = true;

charMap[198] = true; charMap[199] = true; charMap[200] = true; charMap[201] = true;

charMap[202] = true; charMap[203] = true; charMap[204] = true; charMap[205] = true;

charMap[206] = true; charMap[207] = true; charMap[208] = true; charMap[209] = true;

charMap[210] = true; charMap[211] = true; charMap[212] = true; charMap[213] = true;

charMap[214] = true; charMap[215] = true; charMap[216] = true; charMap[217] = true;

charMap[218] = true; charMap[219] = true; charMap[220] = true; charMap[221] = true;

charMap[222] = true; charMap[223] = true; charMap[224] = true; charMap[225] = true;

charMap[226] = true; charMap[227] = true; charMap[228] = true; charMap[229] = true;

charMap[230] = true; charMap[231] = true; charMap[232] = true; charMap[233] = true;

charMap[234] = true; charMap[235] = true; charMap[236] = true; charMap[237] = true;

charMap[238] = true; charMap[239] = true; charMap[240] = true; charMap[241] = true;

charMap[242] = true; charMap[243] = true; charMap[244] = true; charMap[245] = true;

charMap[246] = true; charMap[247] = true; charMap[248] = true; charMap[249] = true;

charMap[250] = true; charMap[251] = true; charMap[252] = true; charMap[253] = true;

charMap[254] = true; charMap[255] = true;

}

* Determines if a char is a valid ISO-8859-1 character.

public boolean isCharValid(char value) {

if (((int)value) < 256 && charMap[(int)value]) {

return true;

} else {

return false;

}

* Returns a string clean of all invalid ISO-8859-1 characters.

public String stripInvalidCharsFromString(String value) {

StringBuffer buffer = new StringBuffer();

char[] charArray = value.toCharArray();

int charArrayLength = charArray.length;

for (int i = 0; i < charArrayLength; i++) {

if (((int)charArray[i]) < 256 && charMap[(int)charArray[i]]) {

buffer.append(charArray[i]);

}

return buffer.toString();

}

Regex Solution

---------------------

// ISOLatin1CharCleaner.java

// Norway

// Created by Eric Stewart on 2/15/06.

import java.util.regex.*;

public class ISOLatin1CharacterUtilityRegex {

private String regExp;

private Pattern p;

public ISOLatin1CharacterUtilityRegex() {

regExp = "[^\\x09\\x0A\\x0D\\x20-\\x7E\\xA0-\\xFF]+";

p = Pattern.compile(regExp);

}

* Returns a string clean of all invalid ISO-8859-1 characters.

public String stripInvalidCharsFromString(String value) {

String result = p.matcher(value).replaceAll("");

return result;

}

 _______________________________________________
Do not post admin requests to the list. They will be ignored.
Webobjects-dev mailing list      (email@hidden)
Help/Unsubscribe/Update your Subscription:

This email sent to email@hidden

Prev by Date: Re: Sophisticated relationship help
Next by Date: Page in Framework not found
Previous by thread: Re: Most efficient character parsing.
Next by thread: Problem with page encoding
Index(es):
- Date
- Thread