From 4b047dba6453ebb964e7300e6f3f1403608d5ff0 Mon Sep 17 00:00:00 2001
From: Travis Wellman <travis@archive.org>
Date: Tue, 3 Jul 2012 13:13:50 -0700
Subject: [PATCH] count path segments by looking at the path

* TooManyPathSegmentsDecideRule
    evaluate(CrawlURI) previously counted slashes in the full URI.
    Now it only counts slashes in the path of the URI, meaning a URI
    with slashes in the query string will not be counted as having more
    path segments than it has in its path.
---
 .../modules/deciderules/TooManyPathSegmentsDecideRule.java  | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/modules/src/main/java/org/archive/modules/deciderules/TooManyPathSegmentsDecideRule.java b/modules/src/main/java/org/archive/modules/deciderules/TooManyPathSegmentsDecideRule.java
index 85268b2d..4ec9e7bb 100644
--- a/modules/src/main/java/org/archive/modules/deciderules/TooManyPathSegmentsDecideRule.java
+++ b/modules/src/main/java/org/archive/modules/deciderules/TooManyPathSegmentsDecideRule.java
@@ -63,11 +63,11 @@ public class TooManyPathSegmentsDecideRule extends PredicatedDecideRule {
      */
     @Override
     protected boolean evaluate(CrawlURI curi) {
-        String uri = curi.toString();
+        String uriPath = curi.getUURI().getEscapedPath();
         int count = 0;
         int threshold = getMaxPathDepth();
-        for (int i = 0; i < uri.length(); i++) {
-            if (uri.charAt(i) == '/') {
+        for (int i = 0; i < uriPath.length(); i++) {
+            if (uriPath.charAt(i) == '/') {
                 count++;
             }
             if (count > threshold) {