Skip to content

Commit

Permalink
allow benchmarking regex variants
Browse files Browse the repository at this point in the history
  • Loading branch information
@seanfabs
sean.fabri authored and seanfabs committed May 9, 2024
1 parent 427b34e commit 59a9c16
Showing 1 changed file with 71 additions and 31 deletions.
102 changes: 71 additions & 31 deletions ...mail2-jakarta/src/test/java/org/apache/commons/mail2/jakarta/ImageHtmlEmailBenchmark.java
View file
Original file line number Diff line number Diff line change
Expand Up @@ -17,50 +17,90 @@
package org.apache.commons.mail2.jakarta;

import org.openjdk.jmh.annotations.Benchmark;
import org.openjdk.jmh.annotations.Scope;
import org.openjdk.jmh.annotations.Setup;
import org.openjdk.jmh.annotations.State;
import org.openjdk.jmh.infra.Blackhole;

import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class ImageHtmlEmailBenchmark {

private final static int MATCHES_TO_FIND = 50;

private final static String TEST_HTML = testHtml();

public final static TestHarness testHarnessCurrentRegex = new TestHarness(
ImageHtmlEmail.REGEX_IMG_SRC,
ImageHtmlEmail.REGEX_SCRIPT_SRC
);

/**
* The original regex pre EMAIL-198
*/
public final static TestHarness testHarnessOriginalRegex = new TestHarness(
"(<[Ii][Mm][Gg]\\s*[^>]*?\\s+[Ss][Rr][Cc]\\s*=\\s*[\"'])([^\"']+?)([\"'])",
"(<[Ss][Cc][Rr][Ii][Pp][Tt]\\s*.*?\\s+[Ss][Rr][Cc]\\s*=\\s*[\"'])([^\"']+?)([\"'])"
);

/**
* Test an alternative regex with a non-greedy url: note the {@code ([^"']+?)} capture.
* This should be slower than the current regex test case.
*/
public final static TestHarness testHarnessCurrentRegexNonGreedyUrl = new TestHarness(
"(<[Ii][Mm][Gg](?=\\s)[^>]*?\\s[Ss][Rr][Cc]\\s*=\\s*[\"'])([^\"']+?)([\"'])",
"(<[Ss][Cc][Rr][Ii][Pp][Tt](?=\\s)[^>]*?\\s[Ss][Rr][Cc]\\s*=\\s*[\"'])([^\"']+?)([\"'])"
);

@Benchmark
public void testCaseCurrentRegex(Blackhole blackhole) {
testHarnessCurrentRegex.runTest(blackhole);
}

@Benchmark
public void testCaseOriginalRegex(Blackhole blackhole) {
testHarnessOriginalRegex.runTest(blackhole);
}

@Benchmark
public void testRegularExpressions(BenchmarkContext context, Blackhole blackhole) {
for (int i = 0; i < context.matchesToFind; i++) {
blackhole.consume(context.matcherImg.find());
blackhole.consume(context.matcherScript.find());
public void testCaseCurrentRegexNonGreedyUrl(Blackhole blackhole) {
testHarnessCurrentRegexNonGreedyUrl.runTest(blackhole);
}

public static class TestHarness {
private Matcher matcherImg;
private Matcher matcherScript;

public TestHarness(String patternImg, String patternScript){
matcherImg = prepareRegex(patternImg);
matcherScript = prepareRegex(patternScript);
}

public void runTest(Blackhole blackhole) {
for (int i = 0; i < MATCHES_TO_FIND; i++) {
blackhole.consume(matcherImg.find());
blackhole.consume(matcherScript.find());
}
matcherImg.reset();
matcherScript.reset();
}

public Matcher prepareRegex(String pattern) {
return Pattern.compile(pattern).matcher(TEST_HTML);
}
context.matcherImg.reset();
context.matcherScript.reset();
}

@State(Scope.Thread)
public static class BenchmarkContext {
Matcher matcherImg;
Matcher matcherScript;
int matchesToFind = 50;

@Setup
public void prepare() {
String longUrl = new String(new char[200]).replace("\0", "a");
String longSpace = new String(new char[100]).replace("\0", " ");
StringBuilder html = new StringBuilder();
html.append("<html><body><pre>");
private static String testHtml() {
String longUrl = new String(new char[200]).replace("\0", "a");
String longSpace = new String(new char[100]).replace("\0", " ");
StringBuilder html = new StringBuilder();
html.append("<html><body><pre>");
html.append("Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.");
for (int i = 0; i < MATCHES_TO_FIND; i++) {
html.append("<img" + longSpace + "xxx=\"no-src-attribute\">");
html.append("<script some=\"true\" other=\"1\" attributes=\"yes\" src = \"" + longUrl + "\">");
html.append("Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.");
for (int i = 0; i < matchesToFind; i++) {
html.append("<img" + longSpace + "xxx=\"no-src-attribute\">");
html.append("<script some=\"true\" other=\"1\" attributes=\"yes\" src = \"" + longUrl + "\">");
html.append("Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.");
}
html.append("</pre></body></html>");
Pattern patternImg = Pattern.compile(ImageHtmlEmail.REGEX_IMG_SRC);
matcherImg = patternImg.matcher(html);
Pattern patternScript = Pattern.compile(ImageHtmlEmail.REGEX_SCRIPT_SRC);
matcherScript = patternScript.matcher(html);
}
html.append("</pre></body></html>");
return html.toString();
}

public static void main(String[] args) throws Exception {
Expand Down

0 comments on commit 59a9c16

Please sign in to comment.