lee/heritrix3
1
0
Fork 0
mirror of https://github.com/internetarchive/heritrix3.git synced 2026-09-25 15:16:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

* ExtractorXML.java

Browse Source 
shouldExtract(CrawlUri) - Avoid java.lang.IndexOutOfBoundsException
    checking for xml preamble in brief/empty url content.
This commit is contained in:
nlevitt
2011-01-03 22:41:00 +00:00
parent ea49e55c89
commit 641f193e17
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/src/main/java/org/archive/modules/extractor/ExtractorXML.java
+2 -2
View File
@@ -66,8 +66,8 @@ public class ExtractorXML extends ContentExtractor {
&& (mimeType.toLowerCase().indexOf("xml") >= 0
|| curi.toString().toLowerCase().endsWith(".rss")
|| curi.toString().toLowerCase().endsWith(".xml")
|| curi.getRecorder().getReplayCharSequence()
.subSequence(0, 8).toString().matches("[\\ufeff]?<\\?xml\\s.*"));
|| (curi.getRecorder().getReplayCharSequence().length() >= 8
&& curi.getRecorder().getReplayCharSequence().subSequence(0, 8).toString().matches("[\\ufeff]?<\\?xml\\s.*")));
} catch (IOException e) {
logger.severe(curi + " - failed getting ReplayCharSequence: " + e);
return false;