lee/heritrix3
1
0
Fork 0
mirror of https://github.com/internetarchive/heritrix3.git synced 2026-09-23 14:15:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

Ensure we start parsing full lines, for #239.

Browse Source
This commit is contained in:
Andrew Jackson
2019-03-13 21:00:19 +09:00
committed by Alex Osborne
parent c40616e494
commit afa88c025e
1 changed files with 6 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
engine/src/main/java/org/archive/crawler/framework/CrawlJob.java
+6
View File
@@ -172,6 +172,12 @@ public class CrawlJob implements Comparable<CrawlJob>, ApplicationListener<Appli
BufferedReader jobLogReader = new BufferedReader(
new InputStreamReader(jobLogIn));
String line;
// If we sliced into the file, make sure we skip to the next line:
// (See https://github.com/internetarchive/heritrix3/issues/239)
if (startPosition != 0) {
line = jobLogReader.readLine();
}
// Parse lines looking for launch details:
while ((line = jobLogReader.readLine()) != null) {
Matcher m = launchLine.matcher(line);
if (m.matches()) {