From: <bra...@us...> - 2010-05-18 22:46:13
|
Revision: 3104 http://archive-access.svn.sourceforge.net/archive-access/?rev=3104&view=rev Author: bradtofel Date: 2010-05-18 22:46:07 +0000 (Tue, 18 May 2010) Log Message: ----------- Translate escaped characters within resolved urls prior to contextualizing. Modified Paths: -------------- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/htmllex/ParseContext.java Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/htmllex/ParseContext.java =================================================================== --- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/htmllex/ParseContext.java 2010-05-18 22:44:22 UTC (rev 3103) +++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/htmllex/ParseContext.java 2010-05-18 22:46:07 UTC (rev 3104) @@ -31,6 +31,7 @@ import org.apache.commons.httpclient.URIException; import org.archive.net.UURI; import org.archive.net.UURIFactory; +import org.htmlparser.util.Translate; /** * Class which tracks the context and state involved with parsing an HTML @@ -93,6 +94,7 @@ * @throws URISyntaxException if the input URL is malformed */ public String resolve(String url) throws URISyntaxException { + url = Translate.decode(url); int hashIdx = url.indexOf('#'); String frag = ""; if(hashIdx != -1) { This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site. |