From 4ffb6865e1cb0b4a002ea661534f0ccba0f4b862 Mon Sep 17 00:00:00 2001 From: Gordon Mohr Date: Thu, 22 Dec 2011 19:04:19 -0800 Subject: [PATCH] [HER-1976] H3: query-portion ignored when checking against robots.txt rules (using only path) * RobotsPolicy.java: use UURI.getPathQuery -- like H1 does --- modules/src/main/java/org/archive/modules/net/RobotsPolicy.java | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/modules/src/main/java/org/archive/modules/net/RobotsPolicy.java b/modules/src/main/java/org/archive/modules/net/RobotsPolicy.java index 1bace024..d4a3a616 100644 --- a/modules/src/main/java/org/archive/modules/net/RobotsPolicy.java +++ b/modules/src/main/java/org/archive/modules/net/RobotsPolicy.java @@ -45,7 +45,7 @@ abstract public class RobotsPolicy { public String getPath(CrawlURI curi) { try { - return curi.getUURI().getPath(); + return curi.getUURI().getPathQuery(); // TODO rename method and change callers; add test } catch (URIException e) { // unlikely return "";