From 458cbb51b0973ebd6eda88c6fb6069e595a4592e Mon Sep 17 00:00:00 2001 From: Adam Miller Date: Thu, 26 Mar 2015 16:19:09 -0700 Subject: [PATCH] Fix for HER-2082 https://webarchive.jira.com/browse/HER-2082 WARCWriterProcessor.java Add last hop character and link context to outlinks in metadata records --- .../java/org/archive/modules/writer/WARCWriterProcessor.java | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/modules/src/main/java/org/archive/modules/writer/WARCWriterProcessor.java b/modules/src/main/java/org/archive/modules/writer/WARCWriterProcessor.java index e50fd051..84aaba37 100644 --- a/modules/src/main/java/org/archive/modules/writer/WARCWriterProcessor.java +++ b/modules/src/main/java/org/archive/modules/writer/WARCWriterProcessor.java @@ -730,7 +730,7 @@ public class WARCWriterProcessor extends WriterPoolProcessor implements WARCWrit Collection links = curi.getOutLinks(); if (links != null && links.size() > 0) { for (CrawlURI link: links) { - r.addLabelValue("outlink", link.getURI()); + r.addLabelValue("outlink", link.getURI()+" "+link.getLastHop()+" "+link.getViaContext()); } }