From 6974abdb95faf27c26d43d00a4ba50737150fa73 Mon Sep 17 00:00:00 2001 From: Athou Date: Thu, 22 Aug 2013 12:04:00 +0200 Subject: [PATCH] don't compare strings with == --- src/main/java/edu/uci/ics/crawler4j/url/URLCanonicalizer.java | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/src/main/java/edu/uci/ics/crawler4j/url/URLCanonicalizer.java b/src/main/java/edu/uci/ics/crawler4j/url/URLCanonicalizer.java index 3f5196a8..d78502d6 100644 --- a/src/main/java/edu/uci/ics/crawler4j/url/URLCanonicalizer.java +++ b/src/main/java/edu/uci/ics/crawler4j/url/URLCanonicalizer.java @@ -28,6 +28,8 @@ import java.util.Map; import java.util.SortedMap; import java.util.TreeMap; +import org.apache.commons.lang.StringUtils; + /** * See http://en.wikipedia.org/wiki/URL_normalization for a reference Note: some * parts of the code are adapted from: http://stackoverflow.com/a/4057470/405418 @@ -46,7 +48,7 @@ public class URLCanonicalizer { URL canonicalURL = new URL(UrlResolver.resolveUrl(context == null ? "" : context, href)); String host = canonicalURL.getHost().toLowerCase(); - if (host == "") { + if (StringUtils.isBlank(host)) { // This is an invalid Url. return null; }