Implement issue #276 exclude certain URLs from checking, also impleme…

docToolchainConfig.groovy

@@ -254,6 +254,8 @@ exportEA.with {
 htmlSanityCheck.with {
     sourceDir = 'microsite/output'
     resultsFolder = 'html-sanity-check'
+    //urlsToExclude = ['http://example.com/excluded', 'http://example.com/excluded2']
+    //hostsToExclude = ['example2.com', 'example3', 'example4']
 }
 //end::htmlSanityCheckConfig[]
 

htmlSanityCheck-core/src/main/java/org/aim42/htmlsanitycheck/Configuration.java

@@ -45,6 +45,9 @@ public class Configuration {
     @Getter(AccessLevel.NONE)
     @Builder.Default
     Boolean ignoreIPAddresses = false;
+    Set<String> urlsToExclude;
+    Set<String> hostsToExclude;
+
     /*
      * Explanation for configuring http status codes:
      * The standard http status codes are defined in class @link NetUtil and can

htmlSanityCheck-core/src/main/java/org/aim42/htmlsanitycheck/check/BrokenHttpLinksChecker.java

@@ -37,6 +37,8 @@ class BrokenHttpLinksChecker extends Checker {
     // need that to calculate "nrOfOccurrences"
     // the pure http/https-hrefs a set, duplicates are removed here
     private Set<String> hrefSet;
+    private Set<String> urlsToExclude;
+    private Set<String> hostsToExclude;
 
 
     BrokenHttpLinksChecker(Configuration pConfig) {
@@ -45,6 +47,8 @@ class BrokenHttpLinksChecker extends Checker {
         errorCodes = getMyConfig().getHttpErrorCodes();
         warningCodes = getMyConfig().getHttpWarningCodes();
         successCodes = getMyConfig().getHttpSuccessCodes();
+        urlsToExclude = getMyConfig().getUrlsToExclude();
+        hostsToExclude = getMyConfig().getHostsToExclude();
     }
 
     @Override
@@ -101,6 +105,25 @@ private void checkAllHttpLinks() {
 
 
     protected void doubleCheckSingleHttpLink(String href) {
+        if (urlsToExclude != null && urlsToExclude.contains(href)) {
+            // Skip checking this URL
+            return;
+        }
+
+        // Check if the host of the URL is in the hostsToExclude list
+        try {
+            URL url = new URL(href);
+            String host = url.getHost();
+            if (hostsToExclude != null && hostsToExclude.contains(host)) {
+                // Skip checking this URL
+                return;
+            }
+        } catch (MalformedURLException e) {
+            // Handle the exception if the URL is malformed
+            Finding malformedURLFinding = new Finding("malformed URL exception with href=" + href);
+            getCheckingResults().addFinding(malformedURLFinding);
+            return;
+        }
         // bookkeeping:
         getCheckingResults().incNrOfChecks();
 

htmlSanityCheck-gradle-plugin/src/main/groovy/org/aim42/htmlsanitycheck/gradle/HtmlSanityCheckTask.groovy

@@ -79,6 +79,12 @@ class HtmlSanityCheckTask extends DefaultTask {
     @Optional
     @Input
     Set<Integer> httpSuccessCodes
+    @Optional
+    @Input
+    Set<String> urlsToExclude
+    @Optional
+    @Input
+    Set<String> hostsToExclude
 
     @Input
     List<Class<? extends Checker>> checkerClasses = AllCheckers.CHECKER_CLASSES
@@ -187,6 +193,8 @@ See ${checkingResultsDir} for a detailed report."""
                 .ignoreIPAddresses(ignoreIPAddresses)
 
                 .checksToExecute(checkerClasses)
+                .urlsToExclude(urlsToExclude)
+                .hostsToExclude(hostsToExclude)
                 .build()
 
         // in case we have configured specific interpretations of http status codes
@@ -212,6 +220,8 @@ See ${checkingResultsDir} for a detailed report."""
         logger.info "Results dir     : $checkingResultsDir"
         logger.info "JUnit dir       : $junitResultsDir"
         logger.info "Fail on errors  : $failOnErrors"
+        logger.info "Urls to Exclude : $urlsToExclude"
+        logger.info "Hosts to Exclude: $hostsToExclude"
     }
 }
 

htmlSanityCheck-gradle-plugin/src/test/groovy/org/aim42/htmlsanitycheck/gradle/HtmlSanityCheckBaseSpec.groovy

@@ -7,6 +7,22 @@ import spock.lang.Specification
 class HtmlSanityCheckBaseSpec extends Specification {
     final static VALID_HTML = """<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"><html><head></head><body></body><html>"""
     final static INVALID_HTML = """<body><span id="id"/><span id="id"/></body> """
+    final static VALID_HTML_WITH_EXCLUDED_URL = """
+        <html>
+        <body>
+        <a href="http://example.com/excluded">Excluded URL</a>
+        <a href="http://example.com/included">Included URL</a>
+        </body>
+        </html>
+    """
+    final static VALID_HTML_WITH_EXCLUDED_HOST = """
+        <html>
+        <body>
+        <a href="http://excluded.com/page">Excluded Host</a>
+        <a href="http://included.com/page">Included Host</a>
+        </body>
+        </html>
+    """
 
     @Rule
     TemporaryFolder testProjectDir = new TemporaryFolder()

htmlSanityCheck-gradle-plugin/src/test/groovy/org/aim42/htmlsanitycheck/gradle/HtmlSanityCheckTaskFunctionalSpec.groovy

@@ -113,6 +113,44 @@ class HtmlSanityCheckTaskFunctionalSpec extends HtmlSanityCheckBaseSpec {
         gradleVersion << GRADLE_VERSIONS
     }
 
+    @Unroll
+    def "can exclude specific URLs with urlsToExclude and Gradle version #gradleVersion"() {
+        given:
+        htmlFile << VALID_HTML_WITH_EXCLUDED_URL
+        createBuildFile("""
+                urlsToExclude = ['http://example.com/excluded']
+        """)
+
+        when:
+        def result = runnerForHtmlSanityCheckTask(gradleVersion as String).build()
+
+        then:
+        result.task(":htmlSanityCheck").outcome == SUCCESS
+        !result.output.contains("http://example.com/excluded")
+
+        where:
+        gradleVersion << GRADLE_VERSIONS
+    }
+
+    @Unroll
+    def "can exclude specific hosts with hostToExclude and Gradle version #gradleVersion"() {
+        given:
+        htmlFile << VALID_HTML_WITH_EXCLUDED_HOST
+        createBuildFile("""
+                hostsToExclude = ['excluded.com']
+        """)
+
+        when:
+        def result = runnerForHtmlSanityCheckTask(gradleVersion as String).build()
+
+        then:
+        result.task(":htmlSanityCheck").outcome == SUCCESS
+        !result.output.contains("http://excluded.com")
+
+        where:
+        gradleVersion << GRADLE_VERSIONS
+    }
+
     private GradleRunner runnerForHtmlSanityCheckTask(String gradleVersion) {
         GradleRunner.create()
                 .withGradleVersion(gradleVersion)

self-check/build.gradle

@@ -11,6 +11,9 @@ htmlSanityCheck {
 
     failOnErrors = true
 
+    urlsToExclude = [ "https://www.aim42.org/"]
+    hostsToExclude = [ "www.aim42.org" ]
+
     logger.quiet "HSC version: ${htmlSanityCheckVersion}"
     logger.quiet "HSC sourceDir: ${sourceDir.absolutePath}"
     logger.quiet "HSC checkingResultsDir: ${checkingResultsDir.absolutePath}"