From 25f7144dacf0f40bc52a42ffaa1913127fbdfa87 Mon Sep 17 00:00:00 2001 From: Shinsuke Sugaya Date: Thu, 26 Sep 2024 10:31:44 +0900 Subject: [PATCH] fix #2844 Ignore case sensitivity in canonical URL comparison to prevent unnecessary redirects --- .../codelibs/fess/crawler/transformer/FessXpathTransformer.java | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/main/java/org/codelibs/fess/crawler/transformer/FessXpathTransformer.java b/src/main/java/org/codelibs/fess/crawler/transformer/FessXpathTransformer.java index 22b299477..541097da4 100644 --- a/src/main/java/org/codelibs/fess/crawler/transformer/FessXpathTransformer.java +++ b/src/main/java/org/codelibs/fess/crawler/transformer/FessXpathTransformer.java @@ -341,7 +341,7 @@ protected Map processAdditionalData(final Map da final Document document) { // canonical final String canonicalUrl = getCanonicalUrl(responseData, document); - if (canonicalUrl != null && !canonicalUrl.equals(responseData.getUrl()) && isValidUrl(canonicalUrl) + if (canonicalUrl != null && !canonicalUrl.equalsIgnoreCase(responseData.getUrl()) && isValidUrl(canonicalUrl) && isValidCanonicalUrl(responseData.getUrl(), canonicalUrl)) { final Set childUrlSet = new HashSet<>(); childUrlSet.add(RequestDataBuilder.newRequestData().get().url(canonicalUrl).build());