Return-Path: Delivered-To: apmail-lucene-java-commits-archive@www.apache.org Received: (qmail 83969 invoked from network); 16 Mar 2007 01:17:18 -0000 Received: from hermes.apache.org (HELO mail.apache.org) (140.211.11.2) by minotaur.apache.org with SMTP; 16 Mar 2007 01:17:18 -0000 Received: (qmail 11235 invoked by uid 500); 16 Mar 2007 01:17:26 -0000 Delivered-To: apmail-lucene-java-commits-archive@lucene.apache.org Received: (qmail 11223 invoked by uid 500); 16 Mar 2007 01:17:26 -0000 Mailing-List: contact java-commits-help@lucene.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: java-dev@lucene.apache.org Delivered-To: mailing list java-commits@lucene.apache.org Received: (qmail 11211 invoked by uid 99); 16 Mar 2007 01:17:26 -0000 Received: from herse.apache.org (HELO herse.apache.org) (140.211.11.133) by apache.org (qpsmtpd/0.29) with ESMTP; Thu, 15 Mar 2007 18:17:26 -0700 X-ASF-Spam-Status: No, hits=-99.5 required=10.0 tests=ALL_TRUSTED,NO_REAL_NAME X-Spam-Check-By: apache.org Received: from [140.211.11.3] (HELO eris.apache.org) (140.211.11.3) by apache.org (qpsmtpd/0.29) with ESMTP; Thu, 15 Mar 2007 18:17:17 -0700 Received: by eris.apache.org (Postfix, from userid 65534) id 23DA31A9838; Thu, 15 Mar 2007 18:16:57 -0700 (PDT) Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: svn commit: r518822 - in /lucene/java/trunk/contrib/benchmark/src/java/org/apache/lucene/benchmark: byTask/feeds/ReutersDocMaker.java byTask/feeds/TrecDocMaker.java standard/StandardBenchmarker.java utils/ExtractReuters.java Date: Fri, 16 Mar 2007 01:16:56 -0000 To: java-commits@lucene.apache.org From: doronc@apache.org X-Mailer: svnmailer-1.1.0 Message-Id: <20070316011657.23DA31A9838@eris.apache.org> X-Virus-Checked: Checked by ClamAV on apache.org Author: doronc Date: Thu Mar 15 18:16:56 2007 New Revision: 518822 URL: http://svn.apache.org/viewvc?view=rev&rev=518822 Log: LUCENE-829: close done readers in contrib/benchmark. Modified: lucene/java/trunk/contrib/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/ReutersDocMaker.java lucene/java/trunk/contrib/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecDocMaker.java lucene/java/trunk/contrib/benchmark/src/java/org/apache/lucene/benchmark/standard/StandardBenchmarker.java lucene/java/trunk/contrib/benchmark/src/java/org/apache/lucene/benchmark/utils/ExtractReuters.java Modified: lucene/java/trunk/contrib/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/ReutersDocMaker.java URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/ReutersDocMaker.java?view=diff&rev=518822&r1=518821&r2=518822 ============================================================================== --- lucene/java/trunk/contrib/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/ReutersDocMaker.java (original) +++ lucene/java/trunk/contrib/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/ReutersDocMaker.java Thu Mar 15 18:16:56 2007 @@ -79,6 +79,7 @@ while ((line = reader.readLine()) != null) { bodyBuf.append(line).append(' '); } + reader.close(); addBytes(f.length()); Modified: lucene/java/trunk/contrib/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecDocMaker.java URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecDocMaker.java?view=diff&rev=518822&r1=518821&r2=518822 ============================================================================== --- lucene/java/trunk/contrib/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecDocMaker.java (original) +++ lucene/java/trunk/contrib/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecDocMaker.java Thu Mar 15 18:16:56 2007 @@ -26,8 +26,10 @@ import java.io.Reader; import java.io.StringReader; import java.text.DateFormat; +import java.text.ParseException; import java.text.SimpleDateFormat; import java.util.ArrayList; +import java.util.Date; import java.util.Locale; import java.util.Properties; import java.util.zip.GZIPInputStream; @@ -159,7 +161,8 @@ read("",null,false,false); // 6. collect until end of doc sb = read("",null,false,true); - // this is the next document, so parse it + // this is the next document, so parse it + // TODO use a more robust html parser (current one aborts parsing quite easily). HTMLParser p = new HTMLParser(new StringReader(sb.toString())); // title String title = p.getTitle(); @@ -175,11 +178,18 @@ bodyBuf.append(c,0,n); } } + r.close(); addBytes(bodyBuf.length()); DocData dd = new DocData(); - - dd.date = dateFormat.parse(dateStr.trim()); + + try { + dd.date = dateFormat.parse(dateStr.trim()); + } catch (ParseException e) { + // do not fail test just because a date could not be parsed + System.out.println("ignoring date parse exception (assigning 'now') for: "+dateStr); + dd.date = new Date(); // now + } dd.name = name; dd.title = title; dd.body = bodyBuf.toString(); Modified: lucene/java/trunk/contrib/benchmark/src/java/org/apache/lucene/benchmark/standard/StandardBenchmarker.java URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/benchmark/src/java/org/apache/lucene/benchmark/standard/StandardBenchmarker.java?view=diff&rev=518822&r1=518821&r2=518822 ============================================================================== --- lucene/java/trunk/contrib/benchmark/src/java/org/apache/lucene/benchmark/standard/StandardBenchmarker.java (original) +++ lucene/java/trunk/contrib/benchmark/src/java/org/apache/lucene/benchmark/standard/StandardBenchmarker.java Thu Mar 15 18:16:56 2007 @@ -275,6 +275,8 @@ { body.append(line).append(' '); } + reader.close(); + Date date = format.parse(dateStr.trim()); doc.add(new Field("date", DateTools.dateToString(date, DateTools.Resolution.SECOND), Field.Store.YES, Field.Index.UN_TOKENIZED)); Modified: lucene/java/trunk/contrib/benchmark/src/java/org/apache/lucene/benchmark/utils/ExtractReuters.java URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/benchmark/src/java/org/apache/lucene/benchmark/utils/ExtractReuters.java?view=diff&rev=518822&r1=518821&r2=518822 ============================================================================== --- lucene/java/trunk/contrib/benchmark/src/java/org/apache/lucene/benchmark/utils/ExtractReuters.java (original) +++ lucene/java/trunk/contrib/benchmark/src/java/org/apache/lucene/benchmark/utils/ExtractReuters.java Thu Mar 15 18:16:56 2007 @@ -135,6 +135,7 @@ buffer.setLength(0); } } + reader.close(); } catch (