Patch a bug introduced by Hadoop 0.4.0, which requires specified input

directories to exist.


git-svn-id: https://svn.apache.org/repos/asf/lucene/nutch/trunk@421185 13f79535-47bb-0310-9956-ffa450edef68

src/java/org/apache/nutch/crawl/CrawlDb.java

@@ -65,15 +65,20 @@ public void update(Path crawlDb, Path segment) throws IOException {
     if (LOG.isInfoEnabled()) { LOG.info("CrawlDb update: done"); }
   }
 
-  public static JobConf createJob(Configuration config, Path crawlDb) {
+  public static JobConf createJob(Configuration config, Path crawlDb)
+    throws IOException {
     Path newCrawlDb =
       new Path(crawlDb,
                Integer.toString(new Random().nextInt(Integer.MAX_VALUE)));
 
     JobConf job = new NutchJob(config);
     job.setJobName("crawldb " + crawlDb);
 
-    job.addInputPath(new Path(crawlDb, CrawlDatum.DB_DIR_NAME));
+
+    Path current = new Path(crawlDb, CrawlDatum.DB_DIR_NAME);
+    if (FileSystem.get(job).exists(current)) {
+      job.addInputPath(current);
+    }
     job.setInputFormat(SequenceFileInputFormat.class);
     job.setInputKeyClass(UTF8.class);
     job.setInputValueClass(CrawlDatum.class);