From 5befd3e4cd2219c5d6aecad02862ba1d97028b44 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Eoghan=20=C3=93=20Carrag=C3=A1in?=
<eoghan.ocarragain@gmail.com>
Date: Fri, 11 Dec 2015 11:27:54 -0500
Subject: [PATCH] Make sure spaces in full text URLs are properly encoded -
Prevents problems when passing them to Tika/Aperture command-line utilities.
---
import/index_scripts/getFulltext.bsh | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/import/index_scripts/getFulltext.bsh b/import/index_scripts/getFulltext.bsh
index 4c24dacfa3e..6385c8640b4 100644
--- a/import/index_scripts/getFulltext.bsh
+++ b/import/index_scripts/getFulltext.bsh
@@ -85,8 +85,8 @@ public String getFulltext(Record record, String fieldSpec, String extension) {
Iterator fieldsIter = fields.iterator();
if (fields != null) {
while(fieldsIter.hasNext()) {
- // Get the current string to work on:
- String current = fieldsIter.next();
+ // Get the current string to work on (and sanitize spaces):
+ String current = fieldsIter.next().replaceAll(" ", "%20");
// Filter by file extension
if (extension == null || current.endsWith(extension)) {
// Load the parser output for each tag into a string
@@ -257,4 +257,4 @@ public String harvestWithParser(url, settings) {
return harvestWithTika(url, settings[1]);
}
return null;
-}
\ No newline at end of file
+}
--
GitLab