fix LineFileDocs to seek to random start on open

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1056702 13f79535-47bb-0310-9956-ffa450edef68

lucene/src/test/org/apache/lucene/index/TestNRTThreads.java

@@ -65,7 +65,7 @@ public class TestNRTThreads extends LuceneTestCase {
       CodecProvider.getDefault().setDefaultFieldCodec("Standard");
     }
 
-    final LineFileDocs docs = new LineFileDocs(true);
+    final LineFileDocs docs = new LineFileDocs(random);
     final File tempDir = _TestUtil.getTempDir("nrtopenfiles");
     final MockDirectoryWrapper dir = new MockDirectoryWrapper(random, FSDirectory.open(tempDir));
     final IndexWriterConfig conf = newIndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer());

lucene/src/test/org/apache/lucene/util/LineFileDocs.java

@@ -18,6 +18,7 @@ package org.apache.lucene.util;
  */
 
 import java.io.Closeable;
+import java.io.File;
 import java.io.FileInputStream;
 import java.io.IOException;
 import java.io.BufferedReader;
@@ -26,6 +27,7 @@ import java.io.InputStream;
 import java.io.BufferedInputStream;
 import java.util.concurrent.atomic.AtomicInteger;
 import java.util.zip.GZIPInputStream;
+import java.util.Random;
 
 import org.apache.lucene.document.Document;
 import org.apache.lucene.document.Field;
@@ -36,21 +38,19 @@ import org.apache.lucene.document.Field;
 public class LineFileDocs implements Closeable {
 
   private BufferedReader reader;
-  private final boolean forever;
   private final static int BUFFER_SIZE = 1 << 16;     // 64K
   private final AtomicInteger id = new AtomicInteger();
   private final String path;
 
   // If forever is true, we rewind the file at EOF (repeat
   // the docs over and over)
-  public LineFileDocs(String path, boolean forever) throws IOException {
+  public LineFileDocs(Random random, String path) throws IOException {
     this.path = path;
-    this.forever = forever;
-    open();
+    open(random);
   }
 
-  public LineFileDocs(boolean forever) throws IOException {
-    this(LuceneTestCase.TEST_LINE_DOCS_FILE, forever);
+  public LineFileDocs(Random random) throws IOException {
+    this(random, LuceneTestCase.TEST_LINE_DOCS_FILE);
   }
 
   public synchronized void close() throws IOException {
@@ -60,22 +60,49 @@ public class LineFileDocs implements Closeable {
     }
   }
 
-  private synchronized void open() throws IOException {
+  private synchronized void open(Random random) throws IOException {
     InputStream is = getClass().getResourceAsStream(path);
     if (is == null) {
       // if its not in classpath, we load it as absolute filesystem path (e.g. Hudson's home dir)
       is = new FileInputStream(path);
     }
+    File file = new File(path);
+    long size;
+    if (file.exists()) {
+      size = file.length();
+    } else {
+      size = is.available();
+    }
     if (path.endsWith(".gz")) {
       is = new GZIPInputStream(is);
+      // guestimate:
+      size *= 2.8;
     }
+
     final InputStream in = new BufferedInputStream(is, BUFFER_SIZE);
     reader = new BufferedReader(new InputStreamReader(in, "UTF-8"), BUFFER_SIZE);
+
+    // Override sizes for currently "known" line files:
+    if (path.equals("europarl.lines.txt.gz")) {
+      size = 15129506L;
+    } else if (path.equals("/home/hudson/lucene-data/enwiki.random.lines.txt.gz")) {
+      size = 3038178822L;
+    }
+
+    // Randomly seek to starting point:
+    if (random != null && size > 3) {
+      final long seekTo = (random.nextLong()&Long.MAX_VALUE) % (size/3);
+      if (LuceneTestCase.VERBOSE) {
+        System.out.println("TEST: LineFileDocs: seek to fp=" + seekTo + " on open");
+      }
+      reader.skip(seekTo);
+      reader.readLine();
+    }
   }
 
-  public synchronized void reset() throws IOException {
+  public synchronized void reset(Random random) throws IOException {
     close();
-    open();
+    open(random);
     id.set(0);
   }
 
@@ -117,15 +144,13 @@ public class LineFileDocs implements Closeable {
     synchronized(this) {
       line = reader.readLine();
       if (line == null) {
-        if (forever) {
-          if (LuceneTestCase.VERBOSE) {
-            System.out.println("TEST: LineFileDocs: now rewind file...");
-          }
-          close();
-          open();
-          line = reader.readLine();
+        // Always rewind at end:
+        if (LuceneTestCase.VERBOSE) {
+          System.out.println("TEST: LineFileDocs: now rewind file...");
         }
-        return null;
+        close();
+        open(null);
+        line = reader.readLine();
       }
     }
 

lucene/src/test/org/apache/lucene/util/automaton/fst/TestFSTs.java

@@ -944,7 +944,7 @@ public class TestFSTs extends LuceneTestCase {
       CodecProvider.getDefault().setDefaultFieldCodec("Standard");
     }
 
-    final LineFileDocs docs = new LineFileDocs(false);
+    final LineFileDocs docs = new LineFileDocs(random);
     final int RUN_TIME_SEC = LuceneTestCase.TEST_NIGHTLY ? 100 : 1;
     final IndexWriterConfig conf = newIndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer()).setMaxBufferedDocs(-1).setRAMBufferSizeMB(64);
     final File tempDir = _TestUtil.getTempDir("fstlines");