You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@lucenenet.apache.org by "Corey Trager (JIRA)" <ji...@apache.org> on 2009/01/18 03:12:59 UTC
[jira] Created: (LUCENENET-169) Changes to make Lucene.NET
compatible with ASP.NET Medium Trust Level, in hosting environments (like
GoDaddy...)
Changes to make Lucene.NET compatible with ASP.NET Medium Trust Level, in hosting environments (like GoDaddy...)
-----------------------------------------------------------------------------------------------------------------
Key: LUCENENET-169
URL: https://issues.apache.org/jira/browse/LUCENENET-169
Project: Lucene.Net
Issue Type: Improvement
Environment: ASP.NET
Reporter: Corey Trager
Microsoft has a configuration file for shared hosting for what they call "Medium Trust". There are a couple places in FSDirectory.cs that violate the restrictions of Medium Trust, but I coded workarounds, shown below.
#1)
// Corey Trager, Oct 2008: Commented call to GetTempPath to workaround permission restrictions at shared host.
// LOCK_DIR isn't used anyway.
public static readonly System.String LOCK_DIR = null; // SupportClass.AppSettings.Get("Lucene.Net.lockDir", System.IO.Path.GetTempPath());
#2)
/// <summary>Returns an array of strings, one for each Lucene index file in the directory. </summary>
public override System.String[] List()
{
/* Changes by Corey Trager, Oct 2008, to workaround permission restrictions at shared host */
System.IO.DirectoryInfo dir = new System.IO.DirectoryInfo(directory.FullName);
System.IO.FileInfo[] files = dir.GetFiles();
string[] list = new string[files.Length];
for (int i = 0; i < files.Length; i++)
{
list[i] = files[i].Name;
}
return list;
/* end of changes */
// System.String[] files = SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName, IndexFileNameFilter.GetFilter());
// for (int i = 0; i < files.Length; i++)
// {
// System.IO.FileInfo fi = new System.IO.FileInfo(files[i]);
// files[i] = fi.Name;
// }
// return files;
}
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
Re: Luke-0.9.x cannot open index files
Posted by Floyd Wu <fl...@gmail.com>.
Hi Digy,
Will this bug affects the normal use of Lucene.Net?
Or this bug will only existed in Luke? It seems that my system work fine
with index contained chinese as field name.
Are there any potential problem if continue using chinese as field name?
Thanks
Floyd
2009/4/25 Digy <di...@gmail.com>
> I think, I found the bug. Here is the dump of the original index:
>
>
>
> NUMDOCS: 3
>
> MAXDOCS: 7
>
> DELETED(0): True
>
> DELETED(1): True
>
> DELETED(2): False
>
> DELETED(3): True
>
> DELETED(4): True
>
> DELETED(5): False
>
> DELETED(6): False
>
> TERM(0): _l_activationdatetime:552877632000000000
>
> TERM(1): _l_author:admin
>
> TERM(2): _l_bookmarkcount:0
>
> TERM(3): _l_clix:0
>
> TERM(4): _l_clix:1
>
> TERM(5): _l_creationdatetime:633427319866778624
>
> TERM(6): _l_creationdatetime:633427324812559872
>
> TERM(7): _l_creationdatetime:633760609388437504
>
> TERM(8): _l_deactivationdatetime:155377824000000000
>
> TERM(9): _l_deactivationdatetime:155378687999969792
>
> TERM(10): _l_document_class:1
>
> TERM(11): _l_document_class:98305
>
> TERM(12): _l_folder:163841
>
> TERM(13): _l_folder:163843
>
> TERM(14): _l_hidden:aaa
>
> TERM(15): _l_last_modified_datetime:633427319866778624
>
> TERM(16): _l_last_modified_datetime:633427324812559872
>
> TERM(17): _l_last_modified_datetime:633760609388437504
>
> TERM(18): _l_meta:abc
>
> TERM(19): _l_meta:abc.ppt
>
> TERM(20): _l_meta:ddx
>
> TERM(21): _l_meta:doc
>
> TERM(22): _l_meta:xyz
>
> TERM(23): _l_meta:名
>
> TERM(24): _l_meta:問
>
> TERM(25): _l_meta:有
>
> TERM(26): _l_meta:檔
>
> TERM(27): _l_meta:測
>
> TERM(28): _l_meta:看
>
> TERM(29): _l_meta:試
>
> TERM(30): _l_meta:還
>
> TERM(31): _l_meta:題
>
> TERM(32): _l_parentdocument:196609
>
> TERM(33): _l_parentdocument:327681
>
> TERM(34): _l_parentdocument:557057
>
> TERM(35): _l_ratingavg:0
>
> TERM(36): _l_ratingmedian:0
>
> TERM(37): _l_ratingstdev:0
>
> TERM(38): _l_ratingsum:0
>
> TERM(39): _l_read_permission:admin
>
> TERM(40): _l_rootdocument:196609
>
> TERM(41): _l_rootdocument:327681
>
> TERM(42): _l_rootdocument:557057
>
> TERM(43): _l_state:0
>
> TERM(44): _l_state:2
>
> TERM(45): _l_summary:2123456789
>
> TERM(46): _l_summary:abc
>
> TERM(47): _l_summary:abc.ppt
>
> TERM(48): _l_summary:ddx
>
> TERM(49): _l_summary:doc
>
> TERM(50): _l_summary:xyz
>
> TERM(51): _l_summary:有
>
> TERM(52): _l_summary:還
>
> TERM(53): _l_title:123
>
> TERM(54): _l_title:class
>
> TERM(55): _l_title:default
>
> TERM(56): _l_title:document
>
> TERM(57): _l_title:名
>
> TERM(58): _l_title:問
>
> TERM(59): _l_title:檔
>
> TERM(60): _l_title:測
>
> TERM(61): _l_title:看
>
> TERM(62): _l_title:試
>
> TERM(63): _l_title:題
>
> TERM(64): _l_unique_key:196609
>
> TERM(65): _l_unique_key:327681
>
> TERM(66): _l_unique_key:557057
>
> TERM(67): _l_version:1
>
> TERM(68): 作者:123
>
> TERM(69): 摘要:2123456789
>
> TERM(70): 摘要:abc
>
> TERM(71): 摘要:abc.ppt
>
> TERM(72): 摘要:ddx
>
> TERM(73): 摘要:doc
>
> TERM(74): 摘要:xyz
>
> TERM(75): 摘要:有
>
> TERM(76): 摘要:還
>
> TERM(77): 標題:123
>
> TERM(78): 標題:class
>
> TERM(79): 標題:default
>
> TERM(80): 標題:document
>
> TERM(81): 標題:名
>
> TERM(82): 標題:問
>
> TERM(83): 標題:檔
>
> TERM(84): 標題:測
>
> TERM(85): 標題:看
>
> TERM(86): 標題:試
>
> TERM(87): 標題:題
>
> TERM(88): 關鍵詞:123
>
>
>
>
>
>
>
> And here is a sample code: read docs from original index and then write to
> an new one.
>
>
>
> void CreateNewIndex(string OrgIndex)
>
> {
>
> IndexReader reader = IndexReader.Open(OrgIndex);
>
> IndexWriter writer = new IndexWriter("Floyd", new
> Lucene.Net.Analysis.WhitespaceAnalyzer(),true);
>
>
>
> for (int i = 0; i < reader.MaxDoc(); i++)
>
> {
>
> if (reader.IsDeleted(i) == true) continue;
>
>
>
> Lucene.Net.Documents.Document orgDoc = reader.Document(i);
>
> System.Collections.IList fields = orgDoc.GetFields();
>
>
>
> Lucene.Net.Documents.Document newDoc = new Document();
>
> foreach (Lucene.Net.Documents.Field field in fields)
>
> {
>
> Lucene.Net.Documents.Field newField = new Field(
>
> System.Convert.ToBase64String(
> System.Text.Encoding.UTF8.GetBytes(field.Name())), //ç
>
> //field.Name(), //ç
>
> field.StringValue(),
>
> field.IsStored() ?
> Lucene.Net.Documents.Field.Store.YES : Lucene.Net.Documents.Field.Store.NO<http://lucene.net.documents.field.store.no/>
> ,
>
> field.IsTokenized() ?
> Lucene.Net.Documents.Field.Index.TOKENIZED :
> Lucene.Net.Documents.Field.Index.UN_TOKENIZED);
>
>
>
> newDoc.Add(newField);
>
> }
>
> writer.AddDocument(newDoc);
>
> }
>
>
>
> writer.Close();
>
> reader.Close();
>
> }
>
>
>
>
>
> If some field names are chinese, then Luke returns “read past EOF”. But if
> those field names are replaced with non-chinese names, then it works.
>
>
>
> DIGY
>
>
>
>
>
>
>
>
>
>
>
> -----Original Message-----
> From: Granroth, Neal V. [mailto:neal.granroth@thermofisher.com]
> Sent: Friday, April 24, 2009 8:53 PM
> To: lucene-net-dev@incubator.apache.org
> Subject: Luke-0.9.x cannot open index files
>
>
>
>
>
> Digy,
>
>
>
> Some additional information from the discussion on the lucene-net-user list
> with Floyd Wu.
>
>
>
>
>
> I ran some further tests using Java Lucene 2.3.2 and JDK 1.5.
>
>
>
> The Java equivalents of the two small test applications I use to inspect an
> index and compact it, function identically to the .NET versions (that were
> built with VS2005 and Lucene.NET 2.3.1).
>
>
>
> That Luke cannot open the index appears to be a problem within Luke.
>
> Even if Floyd's index contains some odd entries, Java Lucene 2.3.2 does not
> flag the index as corrupt; and both the Java and .NET versions report the
> same index content before and after the optimize operation.
>
>
>
>
>
> -- Neal
>
>
>
> **************************************************************
>
> Neal Granroth
>
> Software Engineer, Molecular Spectroscopy
>
> Thermo Fisher Scientific
>
> 5225 Verona Road, Madison, WI 53711
>
>
>
> neal.granroth@thermofisher.com
>
> Tel: 608-276-5645
>
> Fax: 608-276-6328
>
>
>
> www.thermofisher.com
>
>
>
> WORLDWIDE CONFIDENTIALITY NOTE: Dissemination, distribution or copying of
> this e-mail or the information herein by anyone other than the intended
> recipient, or an employee or agent of a system responsible for delivering
> the message to the intended recipient, is prohibited. If you are not the
> intended recipient, please inform the sender and delete all copies.
>
>
>
> -----Original Message-----
>
> From: Digy (JIRA) [mailto:jira@apache.org]
>
> Sent: Wednesday, April 08, 2009 6:28 PM
>
> To: lucene-net-dev@incubator.apache.org
>
> Subject: [jira] Commented: (LUCENENET-169) Changes to make Lucene.NET
> compatible with ASP.NET <http://asp.net/> Medium Trust Level, in hosting
> environments (like GoDaddy...)
>
>
>
>
>
> [
> https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12697335#action_12697335]
>
>
>
> Digy commented on LUCENENET-169:
>
> --------------------------------
>
>
>
> Although you can overcome all of them somehow;
>
>
>
> * controlling the the lifetime of IndexWriter/IndexReader in a naturally
> manner,
>
> * reopening the IndexReader only when needed using (for ex)
> FileSystemWatcher,
>
> * providing a separation between data & bussiness layer,
>
> * providing other apps an interface that may want to write its own user
> interface,
>
> * accessing a single search service from different web apps/from load
> balanced web servers
>
> * controlling the lifetime of searching/indexing code (without being
> effected by the restart of the IIS processes automatically when some memory
> limit is exceeded (for ex.) )
>
> * Ability to access some system resources that can be restricted by IIS
>
> etc.
>
> make me think a separete search service is a better idea.But at last, it is
> a design decision of you.
>
> (Think, A WebApp+Solr in Java world)
>
>
>
>
>
> DIGY
>
>
>
> > Changes to make Lucene.NET compatible with ASP.NET <http://asp.net/> Medium Trust Level, in hosting environments (like GoDaddy...)
>
> >
> -----------------------------------------------------------------------------------------------------------------
>
> >
>
> > Key: LUCENENET-169
>
> > URL: https://issues.apache.org/jira/browse/LUCENENET-169
>
> > Project: Lucene.Net
>
> > Issue Type: Improvement
>
> > Environment: ASP.NET <http://asp.net/>
>
> > Reporter: Corey Trager
>
> > Attachments: FSDirectory.patch
>
> >
>
> >
>
> > Microsoft has a configuration file for shared hosting for what they call
> "Medium Trust". There are a couple places in FSDirectory.cs that violate
> the restrictions of Medium Trust, but I coded workarounds, shown below.
>
> > #1)
>
> > // Corey Trager, Oct 2008: Commented call to GetTempPath to workaround
> permission restrictions at shared host.
>
> > // LOCK_DIR isn't used anyway.
>
> > public static readonly System.String LOCK_DIR = null; //
> SupportClass.AppSettings.Get("Lucene.Net.lockDir",
> System.IO.Path.GetTempPath());
>
> > #2)
>
> > /// <summary>Returns an array of strings, one for each
> Lucene index file in the directory. </summary>
>
> > public override System.String[] List()
>
> > {
>
> > /* Changes by Corey Trager, Oct 2008, to workaround permission
> restrictions at shared host */
>
> > System.IO.DirectoryInfo dir = new
> System.IO.DirectoryInfo(directory.FullName);
>
> > System.IO.FileInfo[] files = dir.GetFiles();
>
> > string[] list = new string[files.Length];
>
> > for (int i = 0; i < files.Length; i++)
>
> > {
>
> > list[i] = files[i].Name;
>
> > }
>
> > return list;
>
> > /* end of changes */
>
> > // System.String[] files =
> SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName,
> IndexFileNameFilter.GetFilter());
>
> > // for (int i = 0; i < files.Length; i++)
>
> > // {
>
> > // System.IO.FileInfo fi = new
> System.IO.FileInfo(files[i]);
>
> > // files[i] = fi.Name;
>
> > // }
>
> > // return files;
>
> > }
>
>
>
> --
>
> This message is automatically generated by JIRA.
>
> -
>
> You can reply to this email to add a comment to the issue online.
>
>
Re: Luke-0.9.x cannot open index files
Posted by Floyd Wu <fl...@gmail.com>.
Hi Neal
Thanks for you help.
2009/4/27 Granroth, Neal V. <ne...@thermofisher.com>
> Floyd,
>
> Here is a simple Java command-line application that displays the content of
> an index. It successfully opens your "documents" index using Java Lucene
> version 2.3.2 (the closest version to current Lucene.NET).
>
> That this program works properly with your index, but Luke does not, shows
> that the problem is within Luke. You can provide this program with your
> index and bug report to the people supporting Luke.
>
> -----------------------------------------------------------------
> package app1;
> import org.apache.lucene.index.*;
> import org.apache.lucene.document.*;
>
> public class Main
> {
> public Main() { }
>
> public static void main(String[] args)
> {
> if (args.length > 0)
> {
> System.out.println("Index Folder: " + args[0]);
>
> IndexReader ird = null;
> try
> {
> ird = IndexReader.open( args[0] );
> System.out.println("Index Version: " + ird.getVersion());
> System.out.println(" isCurrent: " + ird.isCurrent() );
> System.out.println(" isOptimized: " + ird.isOptimized());
> System.out.println(" num Docs: " + ird.numDocs());
> System.out.println(" max Docs: " + ird.maxDoc());
>
> int numDOCs = ird.maxDoc();
> if (numDOCs > 0)
> {
> for(int ii=0; ii<numDOCs; ++ii)
> {
>
> System.out.println("------------------------------------------");
> System.out.println("Doc: " + ii );
> System.out.println(" Deleted: " +
> ird.isDeleted(ii));
> if ( !ird.isDeleted(ii) )
> {
> Document dx = ird.document(ii);
> java.util.List fldList = dx.getFields();
> int numFields = fldList.size();
> for (int nn=0; nn<numFields; ++nn)
> {
> Field xf = (Field) fldList.get(nn);
> String zname = xf.name();
> boolean isStored = xf.isStored();
> boolean isIndexed = xf.isIndexed();
> String zvalue = xf.stringValue();
>
> String scode = (isIndexed ? "I":"N") + "," +
> ( isStored ? "S":"U" );
>
> if (zvalue != null)
> System.out.println(" Field: " + zname
> + ", " + scode + ", Value: " + zvalue);
> else
> System.out.println(" Field: " + zname
> + ", " + scode + ", Value: (none)");
> }
> }
> }
> }
>
>
> System.out.println("------------------------------------------");
> System.out.println("Terms");
>
> System.out.println("------------------------------------------");
>
> TermEnum enuTRM = ird.terms();
> while( enuTRM.next() )
> {
> int freq = enuTRM.docFreq();
> Term oT = enuTRM.term();
> if (oT != null)
> {
> System.out.println(" " + freq + ", " + oT.field() +
> ", \"" + oT.text() + "\"");
> }
> }
>
> ird.close();
> }
> catch(Exception ex)
> {
> System.out.println("Open failed, exception: " +
> ex.toString() );
> }
> }
> }
> }
>
> -----------------------------------------------------------------
>
>
> -- Neal
>
>
> -----Original Message-----
> From: Floyd Wu [mailto:floyd.wu@gmail.com]
> Sent: Monday, April 27, 2009 3:14 AM
> To: lucene-net-dev@incubator.apache.org
> Subject: Re: Luke-0.9.x cannot open index files
>
> Thanks DIGY
> So will you report this to Luke author or Java Lucene group?
> I've been reported this situation to Luke author and he( or she) doesn't
> think this is a bug of Luke.
>
> floyd
>
> 2009/4/27 digy digy <di...@gmail.com>
>
> > It is not a bug of Lucene.Net and as my sample code shows, Lucene.Net
> works
> > well with chinese field names.
> > I think, it is a bug in Luke.
> >
> > DIGY
> >
> >
> >
> > On Mon, Apr 27, 2009 at 8:49 AM, Floyd Wu <fl...@gmail.com> wrote:
> >
> > > Hi Digy,
> > > Thanks for your help.
> > > But if chinese field name is the problem, will it be "fix" in
> Lucene.Net
> > or
> > > how can I avoid this problem.
> > >
> > > Chinese field name is by design and probably not avoidable.
> > >
> > > Floyd
> > >
> > > 2009/4/25 Digy <di...@gmail.com>
> > >
> > > > I think, I found the bug. Here is the dump of the original index:
> > > >
> > > >
> > > >
> > > > NUMDOCS: 3
> > > >
> > > > MAXDOCS: 7
> > > >
> > > > DELETED(0): True
> > > >
> > > > DELETED(1): True
> > > >
> > > > DELETED(2): False
> > > >
> > > > DELETED(3): True
> > > >
> > > > DELETED(4): True
> > > >
> > > > DELETED(5): False
> > > >
> > > > DELETED(6): False
> > > >
> > > > TERM(0): _l_activationdatetime:552877632000000000
> > > >
> > > > TERM(1): _l_author:admin
> > > >
> > > > TERM(2): _l_bookmarkcount:0
> > > >
> > > > TERM(3): _l_clix:0
> > > >
> > > > TERM(4): _l_clix:1
> > > >
> > > > TERM(5): _l_creationdatetime:633427319866778624
> > > >
> > > > TERM(6): _l_creationdatetime:633427324812559872
> > > >
> > > > TERM(7): _l_creationdatetime:633760609388437504
> > > >
> > > > TERM(8): _l_deactivationdatetime:155377824000000000
> > > >
> > > > TERM(9): _l_deactivationdatetime:155378687999969792
> > > >
> > > > TERM(10): _l_document_class:1
> > > >
> > > > TERM(11): _l_document_class:98305
> > > >
> > > > TERM(12): _l_folder:163841
> > > >
> > > > TERM(13): _l_folder:163843
> > > >
> > > > TERM(14): _l_hidden:aaa
> > > >
> > > > TERM(15): _l_last_modified_datetime:633427319866778624
> > > >
> > > > TERM(16): _l_last_modified_datetime:633427324812559872
> > > >
> > > > TERM(17): _l_last_modified_datetime:633760609388437504
> > > >
> > > > TERM(18): _l_meta:abc
> > > >
> > > > TERM(19): _l_meta:abc.ppt
> > > >
> > > > TERM(20): _l_meta:ddx
> > > >
> > > > TERM(21): _l_meta:doc
> > > >
> > > > TERM(22): _l_meta:xyz
> > > >
> > > > TERM(23): _l_meta:名
> > > >
> > > > TERM(24): _l_meta:問
> > > >
> > > > TERM(25): _l_meta:有
> > > >
> > > > TERM(26): _l_meta:檔
> > > >
> > > > TERM(27): _l_meta:測
> > > >
> > > > TERM(28): _l_meta:看
> > > >
> > > > TERM(29): _l_meta:試
> > > >
> > > > TERM(30): _l_meta:還
> > > >
> > > > TERM(31): _l_meta:題
> > > >
> > > > TERM(32): _l_parentdocument:196609
> > > >
> > > > TERM(33): _l_parentdocument:327681
> > > >
> > > > TERM(34): _l_parentdocument:557057
> > > >
> > > > TERM(35): _l_ratingavg:0
> > > >
> > > > TERM(36): _l_ratingmedian:0
> > > >
> > > > TERM(37): _l_ratingstdev:0
> > > >
> > > > TERM(38): _l_ratingsum:0
> > > >
> > > > TERM(39): _l_read_permission:admin
> > > >
> > > > TERM(40): _l_rootdocument:196609
> > > >
> > > > TERM(41): _l_rootdocument:327681
> > > >
> > > > TERM(42): _l_rootdocument:557057
> > > >
> > > > TERM(43): _l_state:0
> > > >
> > > > TERM(44): _l_state:2
> > > >
> > > > TERM(45): _l_summary:2123456789
> > > >
> > > > TERM(46): _l_summary:abc
> > > >
> > > > TERM(47): _l_summary:abc.ppt
> > > >
> > > > TERM(48): _l_summary:ddx
> > > >
> > > > TERM(49): _l_summary:doc
> > > >
> > > > TERM(50): _l_summary:xyz
> > > >
> > > > TERM(51): _l_summary:有
> > > >
> > > > TERM(52): _l_summary:還
> > > >
> > > > TERM(53): _l_title:123
> > > >
> > > > TERM(54): _l_title:class
> > > >
> > > > TERM(55): _l_title:default
> > > >
> > > > TERM(56): _l_title:document
> > > >
> > > > TERM(57): _l_title:名
> > > >
> > > > TERM(58): _l_title:問
> > > >
> > > > TERM(59): _l_title:檔
> > > >
> > > > TERM(60): _l_title:測
> > > >
> > > > TERM(61): _l_title:看
> > > >
> > > > TERM(62): _l_title:試
> > > >
> > > > TERM(63): _l_title:題
> > > >
> > > > TERM(64): _l_unique_key:196609
> > > >
> > > > TERM(65): _l_unique_key:327681
> > > >
> > > > TERM(66): _l_unique_key:557057
> > > >
> > > > TERM(67): _l_version:1
> > > >
> > > > TERM(68): 作者:123
> > > >
> > > > TERM(69): 摘要:2123456789
> > > >
> > > > TERM(70): 摘要:abc
> > > >
> > > > TERM(71): 摘要:abc.ppt
> > > >
> > > > TERM(72): 摘要:ddx
> > > >
> > > > TERM(73): 摘要:doc
> > > >
> > > > TERM(74): 摘要:xyz
> > > >
> > > > TERM(75): 摘要:有
> > > >
> > > > TERM(76): 摘要:還
> > > >
> > > > TERM(77): 標題:123
> > > >
> > > > TERM(78): 標題:class
> > > >
> > > > TERM(79): 標題:default
> > > >
> > > > TERM(80): 標題:document
> > > >
> > > > TERM(81): 標題:名
> > > >
> > > > TERM(82): 標題:問
> > > >
> > > > TERM(83): 標題:檔
> > > >
> > > > TERM(84): 標題:測
> > > >
> > > > TERM(85): 標題:看
> > > >
> > > > TERM(86): 標題:試
> > > >
> > > > TERM(87): 標題:題
> > > >
> > > > TERM(88): 關鍵詞:123
> > > >
> > > >
> > > >
> > > >
> > > >
> > > >
> > > >
> > > > And here is a sample code: read docs from original index and then
> write
> > > to
> > > > an new one.
> > > >
> > > >
> > > >
> > > > void CreateNewIndex(string OrgIndex)
> > > >
> > > > {
> > > >
> > > > IndexReader reader = IndexReader.Open(OrgIndex);
> > > >
> > > > IndexWriter writer = new IndexWriter("Floyd", new
> > > > Lucene.Net.Analysis.WhitespaceAnalyzer(),true);
> > > >
> > > >
> > > >
> > > > for (int i = 0; i < reader.MaxDoc(); i++)
> > > >
> > > > {
> > > >
> > > > if (reader.IsDeleted(i) == true) continue;
> > > >
> > > >
> > > >
> > > > Lucene.Net.Documents.Document orgDoc =
> > > reader.Document(i);
> > > >
> > > > System.Collections.IList fields = orgDoc.GetFields();
> > > >
> > > >
> > > >
> > > > Lucene.Net.Documents.Document newDoc = new Document();
> > > >
> > > > foreach (Lucene.Net.Documents.Field field in fields)
> > > >
> > > > {
> > > >
> > > > Lucene.Net.Documents.Field newField = new Field(
> > > >
> > > > System.Convert.ToBase64String(
> > > > System.Text.Encoding.UTF8.GetBytes(field.Name())), //ç
> > > >
> > > > //field.Name(), //ç
> > > >
> > > > field.StringValue(),
> > > >
> > > > field.IsStored() ?
> > > > Lucene.Net.Documents.Field.Store.YES :
> > > Lucene.Net.Documents.Field.Store.NO<http://lucene.net.documents.field.store.no/>
> <http://lucene.net.documents.field.store.no/>
> > <
> > > http://lucene.net.documents.field.store.no/>
> > > > ,
> > > >
> > > > field.IsTokenized() ?
> > > > Lucene.Net.Documents.Field.Index.TOKENIZED :
> > > > Lucene.Net.Documents.Field.Index.UN_TOKENIZED);
> > > >
> > > >
> > > >
> > > > newDoc.Add(newField);
> > > >
> > > > }
> > > >
> > > > writer.AddDocument(newDoc);
> > > >
> > > > }
> > > >
> > > >
> > > >
> > > > writer.Close();
> > > >
> > > > reader.Close();
> > > >
> > > > }
> > > >
> > > >
> > > >
> > > >
> > > >
> > > > If some field names are chinese, then Luke returns “read past EOF”.
> But
> > > if
> > > > those field names are replaced with non-chinese names, then it works.
> > > >
> > > >
> > > >
> > > > DIGY
> > > >
> > > >
> > > >
> > > >
> > > >
> > > >
> > > >
> > > >
> > > >
> > > >
> > > >
> > > > -----Original Message-----
> > > > From: Granroth, Neal V. [mailto:neal.granroth@thermofisher.com]
> > > > Sent: Friday, April 24, 2009 8:53 PM
> > > > To: lucene-net-dev@incubator.apache.org
> > > > Subject: Luke-0.9.x cannot open index files
> > > >
> > > >
> > > >
> > > >
> > > >
> > > > Digy,
> > > >
> > > >
> > > >
> > > > Some additional information from the discussion on the
> lucene-net-user
> > > list
> > > > with Floyd Wu.
> > > >
> > > >
> > > >
> > > >
> > > >
> > > > I ran some further tests using Java Lucene 2.3.2 and JDK 1.5.
> > > >
> > > >
> > > >
> > > > The Java equivalents of the two small test applications I use to
> > inspect
> > > an
> > > > index and compact it, function identically to the .NET versions (that
> > > were
> > > > built with VS2005 and Lucene.NET 2.3.1).
> > > >
> > > >
> > > >
> > > > That Luke cannot open the index appears to be a problem within Luke.
> > > >
> > > > Even if Floyd's index contains some odd entries, Java Lucene 2.3.2
> does
> > > not
> > > > flag the index as corrupt; and both the Java and .NET versions report
> > the
> > > > same index content before and after the optimize operation.
> > > >
> > > >
> > > >
> > > >
> > > >
> > > > -- Neal
> > > >
> > > >
> > > >
> > > > -----Original Message-----
> > > >
> > > > From: Digy (JIRA) [mailto:jira@apache.org]
> > > >
> > > > Sent: Wednesday, April 08, 2009 6:28 PM
> > > >
> > > > To: lucene-net-dev@incubator.apache.org
> > > >
> > > > Subject: [jira] Commented: (LUCENENET-169) Changes to make Lucene.NET
> > > > compatible with ASP.NET <http://asp.net/> <http://asp.net/> <
> http://asp.net/> Medium
> > Trust Level, in hosting
> > > > environments (like GoDaddy...)
> > > >
> > > >
> > > >
> > > >
> > > >
> > > > [
> > > >
> > >
> >
> https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12697335#action_12697335
> > > ]
> > > >
> > > >
> > > >
> > > > Digy commented on LUCENENET-169:
> > > >
> > > > --------------------------------
> > > >
> > > >
> > > >
> > > > Although you can overcome all of them somehow;
> > > >
> > > >
> > > >
> > > > * controlling the the lifetime of IndexWriter/IndexReader in a
> > naturally
> > > > manner,
> > > >
> > > > * reopening the IndexReader only when needed using (for ex)
> > > > FileSystemWatcher,
> > > >
> > > > * providing a separation between data & bussiness layer,
> > > >
> > > > * providing other apps an interface that may want to write its own
> user
> > > > interface,
> > > >
> > > > * accessing a single search service from different web apps/from load
> > > > balanced web servers
> > > >
> > > > * controlling the lifetime of searching/indexing code (without being
> > > > effected by the restart of the IIS processes automatically when some
> > > memory
> > > > limit is exceeded (for ex.) )
> > > >
> > > > * Ability to access some system resources that can be restricted by
> IIS
> > > >
> > > > etc.
> > > >
> > > > make me think a separete search service is a better idea.But at last,
> > it
> > > is
> > > > a design decision of you.
> > > >
> > > > (Think, A WebApp+Solr in Java world)
> > > >
> > > >
> > > >
> > > >
> > > >
> > > > DIGY
> > > >
> > > >
> > > >
> > > > > Changes to make Lucene.NET compatible with ASP.NET<http://asp.net/><
> http://asp.net/><
> > http://asp.net/>
> > > Medium Trust Level, in hosting environments (like GoDaddy...)
> > > >
> > > > >
> > > >
> > >
> >
> -----------------------------------------------------------------------------------------------------------------
> > > >
> > > > >
> > > >
> > > > > Key: LUCENENET-169
> > > >
> > > > > URL:
> > > https://issues.apache.org/jira/browse/LUCENENET-169
> > > >
> > > > > Project: Lucene.Net
> > > >
> > > > > Issue Type: Improvement
> > > >
> > > > > Environment: ASP.NET <http://asp.net/> <http://asp.net/> <
> http://asp.net/>
> > > >
> > > > > Reporter: Corey Trager
> > > >
> > > > > Attachments: FSDirectory.patch
> > > >
> > > > >
> > > >
> > > > >
> > > >
> > > > > Microsoft has a configuration file for shared hosting for what they
> > > call
> > > > "Medium Trust". There are a couple places in FSDirectory.cs that
> > > violate
> > > > the restrictions of Medium Trust, but I coded workarounds, shown
> below.
> > > >
> > > > > #1)
> > > >
> > > > > // Corey Trager, Oct 2008: Commented call to GetTempPath to
> > workaround
> > > > permission restrictions at shared host.
> > > >
> > > > > // LOCK_DIR isn't used anyway.
> > > >
> > > > > public static readonly System.String LOCK_DIR = null; //
> > > > SupportClass.AppSettings.Get("Lucene.Net.lockDir",
> > > > System.IO.Path.GetTempPath());
> > > >
> > > > > #2)
> > > >
> > > > > /// <summary>Returns an array of strings, one for
> each
> > > > Lucene index file in the directory. </summary>
> > > >
> > > > > public override System.String[] List()
> > > >
> > > > > {
> > > >
> > > > > /* Changes by Corey Trager, Oct 2008, to workaround permission
> > > > restrictions at shared host */
> > > >
> > > > > System.IO.DirectoryInfo dir = new
> > > > System.IO.DirectoryInfo(directory.FullName);
> > > >
> > > > > System.IO.FileInfo[] files = dir.GetFiles();
> > > >
> > > > > string[] list = new string[files.Length];
> > > >
> > > > > for (int i = 0; i < files.Length; i++)
> > > >
> > > > > {
> > > >
> > > > > list[i] = files[i].Name;
> > > >
> > > > > }
> > > >
> > > > > return list;
> > > >
> > > > > /* end of changes */
> > > >
> > > > > // System.String[] files =
> > > > SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName,
> > > > IndexFileNameFilter.GetFilter());
> > > >
> > > > > // for (int i = 0; i < files.Length; i++)
> > > >
> > > > > // {
> > > >
> > > > > // System.IO.FileInfo fi = new
> > > > System.IO.FileInfo(files[i]);
> > > >
> > > > > // files[i] = fi.Name;
> > > >
> > > > > // }
> > > >
> > > > > // return files;
> > > >
> > > > > }
> > > >
> > > >
> > > >
> > > > --
> > > >
> > > > This message is automatically generated by JIRA.
> > > >
> > > > -
> > > >
> > > > You can reply to this email to add a comment to the issue online.
> > > >
> > > >
> > >
> >
>
RE: Luke-0.9.x cannot open index files
Posted by Digy <di...@gmail.com>.
https://issues.apache.org/jira/browse/LUCENE-1623
DIGY
-----Original Message-----
From: Granroth, Neal V. [mailto:neal.granroth@thermofisher.com]
Sent: Monday, April 27, 2009 5:58 PM
To: lucene-net-dev@incubator.apache.org
Subject: RE: Luke-0.9.x cannot open index files
Floyd,
Here is a simple Java command-line application that displays the content of an index. It successfully opens your "documents" index using Java Lucene version 2.3.2 (the closest version to current Lucene.NET).
That this program works properly with your index, but Luke does not, shows that the problem is within Luke. You can provide this program with your index and bug report to the people supporting Luke.
-----------------------------------------------------------------
package app1;
import org.apache.lucene.index.*;
import org.apache.lucene.document.*;
public class Main
{
public Main() { }
public static void main(String[] args)
{
if (args.length > 0)
{
System.out.println("Index Folder: " + args[0]);
IndexReader ird = null;
try
{
ird = IndexReader.open( args[0] );
System.out.println("Index Version: " + ird.getVersion());
System.out.println(" isCurrent: " + ird.isCurrent() );
System.out.println(" isOptimized: " + ird.isOptimized());
System.out.println(" num Docs: " + ird.numDocs());
System.out.println(" max Docs: " + ird.maxDoc());
int numDOCs = ird.maxDoc();
if (numDOCs > 0)
{
for(int ii=0; ii<numDOCs; ++ii)
{
System.out.println("------------------------------------------");
System.out.println("Doc: " + ii );
System.out.println(" Deleted: " + ird.isDeleted(ii));
if ( !ird.isDeleted(ii) )
{
Document dx = ird.document(ii);
java.util.List fldList = dx.getFields();
int numFields = fldList.size();
for (int nn=0; nn<numFields; ++nn)
{
Field xf = (Field) fldList.get(nn);
String zname = xf.name();
boolean isStored = xf.isStored();
boolean isIndexed = xf.isIndexed();
String zvalue = xf.stringValue();
String scode = (isIndexed ? "I":"N") + "," + ( isStored ? "S":"U" );
if (zvalue != null)
System.out.println(" Field: " + zname + ", " + scode + ", Value: " + zvalue);
else
System.out.println(" Field: " + zname + ", " + scode + ", Value: (none)");
}
}
}
}
System.out.println("------------------------------------------");
System.out.println("Terms");
System.out.println("------------------------------------------");
TermEnum enuTRM = ird.terms();
while( enuTRM.next() )
{
int freq = enuTRM.docFreq();
Term oT = enuTRM.term();
if (oT != null)
{
System.out.println(" " + freq + ", " + oT.field() + ", \"" + oT.text() + "\"");
}
}
ird.close();
}
catch(Exception ex)
{
System.out.println("Open failed, exception: " + ex.toString() );
}
}
}
}
-----------------------------------------------------------------
-- Neal
-----Original Message-----
From: Floyd Wu [mailto:floyd.wu@gmail.com]
Sent: Monday, April 27, 2009 3:14 AM
To: lucene-net-dev@incubator.apache.org
Subject: Re: Luke-0.9.x cannot open index files
Thanks DIGY
So will you report this to Luke author or Java Lucene group?
I've been reported this situation to Luke author and he( or she) doesn't
think this is a bug of Luke.
floyd
2009/4/27 digy digy <di...@gmail.com>
> It is not a bug of Lucene.Net and as my sample code shows, Lucene.Net works
> well with chinese field names.
> I think, it is a bug in Luke.
>
> DIGY
>
>
>
> On Mon, Apr 27, 2009 at 8:49 AM, Floyd Wu <fl...@gmail.com> wrote:
>
> > Hi Digy,
> > Thanks for your help.
> > But if chinese field name is the problem, will it be "fix" in Lucene.Net
> or
> > how can I avoid this problem.
> >
> > Chinese field name is by design and probably not avoidable.
> >
> > Floyd
> >
> > 2009/4/25 Digy <di...@gmail.com>
> >
> > > I think, I found the bug. Here is the dump of the original index:
> > >
> > >
> > >
> > > NUMDOCS: 3
> > >
> > > MAXDOCS: 7
> > >
> > > DELETED(0): True
> > >
> > > DELETED(1): True
> > >
> > > DELETED(2): False
> > >
> > > DELETED(3): True
> > >
> > > DELETED(4): True
> > >
> > > DELETED(5): False
> > >
> > > DELETED(6): False
> > >
> > > TERM(0): _l_activationdatetime:552877632000000000
> > >
> > > TERM(1): _l_author:admin
> > >
> > > TERM(2): _l_bookmarkcount:0
> > >
> > > TERM(3): _l_clix:0
> > >
> > > TERM(4): _l_clix:1
> > >
> > > TERM(5): _l_creationdatetime:633427319866778624
> > >
> > > TERM(6): _l_creationdatetime:633427324812559872
> > >
> > > TERM(7): _l_creationdatetime:633760609388437504
> > >
> > > TERM(8): _l_deactivationdatetime:155377824000000000
> > >
> > > TERM(9): _l_deactivationdatetime:155378687999969792
> > >
> > > TERM(10): _l_document_class:1
> > >
> > > TERM(11): _l_document_class:98305
> > >
> > > TERM(12): _l_folder:163841
> > >
> > > TERM(13): _l_folder:163843
> > >
> > > TERM(14): _l_hidden:aaa
> > >
> > > TERM(15): _l_last_modified_datetime:633427319866778624
> > >
> > > TERM(16): _l_last_modified_datetime:633427324812559872
> > >
> > > TERM(17): _l_last_modified_datetime:633760609388437504
> > >
> > > TERM(18): _l_meta:abc
> > >
> > > TERM(19): _l_meta:abc.ppt
> > >
> > > TERM(20): _l_meta:ddx
> > >
> > > TERM(21): _l_meta:doc
> > >
> > > TERM(22): _l_meta:xyz
> > >
> > > TERM(23): _l_meta:名
> > >
> > > TERM(24): _l_meta:問
> > >
> > > TERM(25): _l_meta:有
> > >
> > > TERM(26): _l_meta:檔
> > >
> > > TERM(27): _l_meta:測
> > >
> > > TERM(28): _l_meta:看
> > >
> > > TERM(29): _l_meta:試
> > >
> > > TERM(30): _l_meta:還
> > >
> > > TERM(31): _l_meta:題
> > >
> > > TERM(32): _l_parentdocument:196609
> > >
> > > TERM(33): _l_parentdocument:327681
> > >
> > > TERM(34): _l_parentdocument:557057
> > >
> > > TERM(35): _l_ratingavg:0
> > >
> > > TERM(36): _l_ratingmedian:0
> > >
> > > TERM(37): _l_ratingstdev:0
> > >
> > > TERM(38): _l_ratingsum:0
> > >
> > > TERM(39): _l_read_permission:admin
> > >
> > > TERM(40): _l_rootdocument:196609
> > >
> > > TERM(41): _l_rootdocument:327681
> > >
> > > TERM(42): _l_rootdocument:557057
> > >
> > > TERM(43): _l_state:0
> > >
> > > TERM(44): _l_state:2
> > >
> > > TERM(45): _l_summary:2123456789
> > >
> > > TERM(46): _l_summary:abc
> > >
> > > TERM(47): _l_summary:abc.ppt
> > >
> > > TERM(48): _l_summary:ddx
> > >
> > > TERM(49): _l_summary:doc
> > >
> > > TERM(50): _l_summary:xyz
> > >
> > > TERM(51): _l_summary:有
> > >
> > > TERM(52): _l_summary:還
> > >
> > > TERM(53): _l_title:123
> > >
> > > TERM(54): _l_title:class
> > >
> > > TERM(55): _l_title:default
> > >
> > > TERM(56): _l_title:document
> > >
> > > TERM(57): _l_title:名
> > >
> > > TERM(58): _l_title:問
> > >
> > > TERM(59): _l_title:檔
> > >
> > > TERM(60): _l_title:測
> > >
> > > TERM(61): _l_title:看
> > >
> > > TERM(62): _l_title:試
> > >
> > > TERM(63): _l_title:題
> > >
> > > TERM(64): _l_unique_key:196609
> > >
> > > TERM(65): _l_unique_key:327681
> > >
> > > TERM(66): _l_unique_key:557057
> > >
> > > TERM(67): _l_version:1
> > >
> > > TERM(68): 作者:123
> > >
> > > TERM(69): 摘要:2123456789
> > >
> > > TERM(70): 摘要:abc
> > >
> > > TERM(71): 摘要:abc.ppt
> > >
> > > TERM(72): 摘要:ddx
> > >
> > > TERM(73): 摘要:doc
> > >
> > > TERM(74): 摘要:xyz
> > >
> > > TERM(75): 摘要:有
> > >
> > > TERM(76): 摘要:還
> > >
> > > TERM(77): 標題:123
> > >
> > > TERM(78): 標題:class
> > >
> > > TERM(79): 標題:default
> > >
> > > TERM(80): 標題:document
> > >
> > > TERM(81): 標題:名
> > >
> > > TERM(82): 標題:問
> > >
> > > TERM(83): 標題:檔
> > >
> > > TERM(84): 標題:測
> > >
> > > TERM(85): 標題:看
> > >
> > > TERM(86): 標題:試
> > >
> > > TERM(87): 標題:題
> > >
> > > TERM(88): 關鍵詞:123
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > > And here is a sample code: read docs from original index and then write
> > to
> > > an new one.
> > >
> > >
> > >
> > > void CreateNewIndex(string OrgIndex)
> > >
> > > {
> > >
> > > IndexReader reader = IndexReader.Open(OrgIndex);
> > >
> > > IndexWriter writer = new IndexWriter("Floyd", new
> > > Lucene.Net.Analysis.WhitespaceAnalyzer(),true);
> > >
> > >
> > >
> > > for (int i = 0; i < reader.MaxDoc(); i++)
> > >
> > > {
> > >
> > > if (reader.IsDeleted(i) == true) continue;
> > >
> > >
> > >
> > > Lucene.Net.Documents.Document orgDoc =
> > reader.Document(i);
> > >
> > > System.Collections.IList fields = orgDoc.GetFields();
> > >
> > >
> > >
> > > Lucene.Net.Documents.Document newDoc = new Document();
> > >
> > > foreach (Lucene.Net.Documents.Field field in fields)
> > >
> > > {
> > >
> > > Lucene.Net.Documents.Field newField = new Field(
> > >
> > > System.Convert.ToBase64String(
> > > System.Text.Encoding.UTF8.GetBytes(field.Name())), //ç
> > >
> > > //field.Name(), //ç
> > >
> > > field.StringValue(),
> > >
> > > field.IsStored() ?
> > > Lucene.Net.Documents.Field.Store.YES :
> > Lucene.Net.Documents.Field.Store.NO<http://lucene.net.documents.field.store.no/>
> <
> > http://lucene.net.documents.field.store.no/>
> > > ,
> > >
> > > field.IsTokenized() ?
> > > Lucene.Net.Documents.Field.Index.TOKENIZED :
> > > Lucene.Net.Documents.Field.Index.UN_TOKENIZED);
> > >
> > >
> > >
> > > newDoc.Add(newField);
> > >
> > > }
> > >
> > > writer.AddDocument(newDoc);
> > >
> > > }
> > >
> > >
> > >
> > > writer.Close();
> > >
> > > reader.Close();
> > >
> > > }
> > >
> > >
> > >
> > >
> > >
> > > If some field names are chinese, then Luke returns “read past EOF”. But
> > if
> > > those field names are replaced with non-chinese names, then it works.
> > >
> > >
> > >
> > > DIGY
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > > -----Original Message-----
> > > From: Granroth, Neal V. [mailto:neal.granroth@thermofisher.com]
> > > Sent: Friday, April 24, 2009 8:53 PM
> > > To: lucene-net-dev@incubator.apache.org
> > > Subject: Luke-0.9.x cannot open index files
> > >
> > >
> > >
> > >
> > >
> > > Digy,
> > >
> > >
> > >
> > > Some additional information from the discussion on the lucene-net-user
> > list
> > > with Floyd Wu.
> > >
> > >
> > >
> > >
> > >
> > > I ran some further tests using Java Lucene 2.3.2 and JDK 1.5.
> > >
> > >
> > >
> > > The Java equivalents of the two small test applications I use to
> inspect
> > an
> > > index and compact it, function identically to the .NET versions (that
> > were
> > > built with VS2005 and Lucene.NET 2.3.1).
> > >
> > >
> > >
> > > That Luke cannot open the index appears to be a problem within Luke.
> > >
> > > Even if Floyd's index contains some odd entries, Java Lucene 2.3.2 does
> > not
> > > flag the index as corrupt; and both the Java and .NET versions report
> the
> > > same index content before and after the optimize operation.
> > >
> > >
> > >
> > >
> > >
> > > -- Neal
> > >
> > >
> > >
> > > -----Original Message-----
> > >
> > > From: Digy (JIRA) [mailto:jira@apache.org]
> > >
> > > Sent: Wednesday, April 08, 2009 6:28 PM
> > >
> > > To: lucene-net-dev@incubator.apache.org
> > >
> > > Subject: [jira] Commented: (LUCENENET-169) Changes to make Lucene.NET
> > > compatible with ASP.NET <http://asp.net/> <http://asp.net/> Medium
> Trust Level, in hosting
> > > environments (like GoDaddy...)
> > >
> > >
> > >
> > >
> > >
> > > [
> > >
> >
> https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12697335#action_12697335
> > ]
> > >
> > >
> > >
> > > Digy commented on LUCENENET-169:
> > >
> > > --------------------------------
> > >
> > >
> > >
> > > Although you can overcome all of them somehow;
> > >
> > >
> > >
> > > * controlling the the lifetime of IndexWriter/IndexReader in a
> naturally
> > > manner,
> > >
> > > * reopening the IndexReader only when needed using (for ex)
> > > FileSystemWatcher,
> > >
> > > * providing a separation between data & bussiness layer,
> > >
> > > * providing other apps an interface that may want to write its own user
> > > interface,
> > >
> > > * accessing a single search service from different web apps/from load
> > > balanced web servers
> > >
> > > * controlling the lifetime of searching/indexing code (without being
> > > effected by the restart of the IIS processes automatically when some
> > memory
> > > limit is exceeded (for ex.) )
> > >
> > > * Ability to access some system resources that can be restricted by IIS
> > >
> > > etc.
> > >
> > > make me think a separete search service is a better idea.But at last,
> it
> > is
> > > a design decision of you.
> > >
> > > (Think, A WebApp+Solr in Java world)
> > >
> > >
> > >
> > >
> > >
> > > DIGY
> > >
> > >
> > >
> > > > Changes to make Lucene.NET compatible with ASP.NET <http://asp.net/><
> http://asp.net/>
> > Medium Trust Level, in hosting environments (like GoDaddy...)
> > >
> > > >
> > >
> >
> -----------------------------------------------------------------------------------------------------------------
> > >
> > > >
> > >
> > > > Key: LUCENENET-169
> > >
> > > > URL:
> > https://issues.apache.org/jira/browse/LUCENENET-169
> > >
> > > > Project: Lucene.Net
> > >
> > > > Issue Type: Improvement
> > >
> > > > Environment: ASP.NET <http://asp.net/> <http://asp.net/>
> > >
> > > > Reporter: Corey Trager
> > >
> > > > Attachments: FSDirectory.patch
> > >
> > > >
> > >
> > > >
> > >
> > > > Microsoft has a configuration file for shared hosting for what they
> > call
> > > "Medium Trust". There are a couple places in FSDirectory.cs that
> > violate
> > > the restrictions of Medium Trust, but I coded workarounds, shown below.
> > >
> > > > #1)
> > >
> > > > // Corey Trager, Oct 2008: Commented call to GetTempPath to
> workaround
> > > permission restrictions at shared host.
> > >
> > > > // LOCK_DIR isn't used anyway.
> > >
> > > > public static readonly System.String LOCK_DIR = null; //
> > > SupportClass.AppSettings.Get("Lucene.Net.lockDir",
> > > System.IO.Path.GetTempPath());
> > >
> > > > #2)
> > >
> > > > /// <summary>Returns an array of strings, one for each
> > > Lucene index file in the directory. </summary>
> > >
> > > > public override System.String[] List()
> > >
> > > > {
> > >
> > > > /* Changes by Corey Trager, Oct 2008, to workaround permission
> > > restrictions at shared host */
> > >
> > > > System.IO.DirectoryInfo dir = new
> > > System.IO.DirectoryInfo(directory.FullName);
> > >
> > > > System.IO.FileInfo[] files = dir.GetFiles();
> > >
> > > > string[] list = new string[files.Length];
> > >
> > > > for (int i = 0; i < files.Length; i++)
> > >
> > > > {
> > >
> > > > list[i] = files[i].Name;
> > >
> > > > }
> > >
> > > > return list;
> > >
> > > > /* end of changes */
> > >
> > > > // System.String[] files =
> > > SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName,
> > > IndexFileNameFilter.GetFilter());
> > >
> > > > // for (int i = 0; i < files.Length; i++)
> > >
> > > > // {
> > >
> > > > // System.IO.FileInfo fi = new
> > > System.IO.FileInfo(files[i]);
> > >
> > > > // files[i] = fi.Name;
> > >
> > > > // }
> > >
> > > > // return files;
> > >
> > > > }
> > >
> > >
> > >
> > > --
> > >
> > > This message is automatically generated by JIRA.
> > >
> > > -
> > >
> > > You can reply to this email to add a comment to the issue online.
> > >
> > >
> >
>
RE: Luke-0.9.x cannot open index files
Posted by Digy <di...@gmail.com>.
Please see the thread "Read past EOF"
http://mail-archives.apache.org/mod_mbox/lucene-java-user/200904.mbox/%3C9ac0c6aa0904280715m6f762016id7c2de7acb627d8@mail.gmail.com%3E
DIGY
-----Original Message-----
From: Granroth, Neal V. [mailto:neal.granroth@thermofisher.com]
Sent: Monday, April 27, 2009 5:58 PM
To: lucene-net-dev@incubator.apache.org
Subject: RE: Luke-0.9.x cannot open index files
Floyd,
Here is a simple Java command-line application that displays the content of an index. It successfully opens your "documents" index using Java Lucene version 2.3.2 (the closest version to current Lucene.NET).
That this program works properly with your index, but Luke does not, shows that the problem is within Luke. You can provide this program with your index and bug report to the people supporting Luke.
-----------------------------------------------------------------
package app1;
import org.apache.lucene.index.*;
import org.apache.lucene.document.*;
public class Main
{
public Main() { }
public static void main(String[] args)
{
if (args.length > 0)
{
System.out.println("Index Folder: " + args[0]);
IndexReader ird = null;
try
{
ird = IndexReader.open( args[0] );
System.out.println("Index Version: " + ird.getVersion());
System.out.println(" isCurrent: " + ird.isCurrent() );
System.out.println(" isOptimized: " + ird.isOptimized());
System.out.println(" num Docs: " + ird.numDocs());
System.out.println(" max Docs: " + ird.maxDoc());
int numDOCs = ird.maxDoc();
if (numDOCs > 0)
{
for(int ii=0; ii<numDOCs; ++ii)
{
System.out.println("------------------------------------------");
System.out.println("Doc: " + ii );
System.out.println(" Deleted: " + ird.isDeleted(ii));
if ( !ird.isDeleted(ii) )
{
Document dx = ird.document(ii);
java.util.List fldList = dx.getFields();
int numFields = fldList.size();
for (int nn=0; nn<numFields; ++nn)
{
Field xf = (Field) fldList.get(nn);
String zname = xf.name();
boolean isStored = xf.isStored();
boolean isIndexed = xf.isIndexed();
String zvalue = xf.stringValue();
String scode = (isIndexed ? "I":"N") + "," + ( isStored ? "S":"U" );
if (zvalue != null)
System.out.println(" Field: " + zname + ", " + scode + ", Value: " + zvalue);
else
System.out.println(" Field: " + zname + ", " + scode + ", Value: (none)");
}
}
}
}
System.out.println("------------------------------------------");
System.out.println("Terms");
System.out.println("------------------------------------------");
TermEnum enuTRM = ird.terms();
while( enuTRM.next() )
{
int freq = enuTRM.docFreq();
Term oT = enuTRM.term();
if (oT != null)
{
System.out.println(" " + freq + ", " + oT.field() + ", \"" + oT.text() + "\"");
}
}
ird.close();
}
catch(Exception ex)
{
System.out.println("Open failed, exception: " + ex.toString() );
}
}
}
}
-----------------------------------------------------------------
-- Neal
-----Original Message-----
From: Floyd Wu [mailto:floyd.wu@gmail.com]
Sent: Monday, April 27, 2009 3:14 AM
To: lucene-net-dev@incubator.apache.org
Subject: Re: Luke-0.9.x cannot open index files
Thanks DIGY
So will you report this to Luke author or Java Lucene group?
I've been reported this situation to Luke author and he( or she) doesn't
think this is a bug of Luke.
floyd
2009/4/27 digy digy <di...@gmail.com>
> It is not a bug of Lucene.Net and as my sample code shows, Lucene.Net works
> well with chinese field names.
> I think, it is a bug in Luke.
>
> DIGY
>
>
>
> On Mon, Apr 27, 2009 at 8:49 AM, Floyd Wu <fl...@gmail.com> wrote:
>
> > Hi Digy,
> > Thanks for your help.
> > But if chinese field name is the problem, will it be "fix" in Lucene.Net
> or
> > how can I avoid this problem.
> >
> > Chinese field name is by design and probably not avoidable.
> >
> > Floyd
> >
> > 2009/4/25 Digy <di...@gmail.com>
> >
> > > I think, I found the bug. Here is the dump of the original index:
> > >
> > >
> > >
> > > NUMDOCS: 3
> > >
> > > MAXDOCS: 7
> > >
> > > DELETED(0): True
> > >
> > > DELETED(1): True
> > >
> > > DELETED(2): False
> > >
> > > DELETED(3): True
> > >
> > > DELETED(4): True
> > >
> > > DELETED(5): False
> > >
> > > DELETED(6): False
> > >
> > > TERM(0): _l_activationdatetime:552877632000000000
> > >
> > > TERM(1): _l_author:admin
> > >
> > > TERM(2): _l_bookmarkcount:0
> > >
> > > TERM(3): _l_clix:0
> > >
> > > TERM(4): _l_clix:1
> > >
> > > TERM(5): _l_creationdatetime:633427319866778624
> > >
> > > TERM(6): _l_creationdatetime:633427324812559872
> > >
> > > TERM(7): _l_creationdatetime:633760609388437504
> > >
> > > TERM(8): _l_deactivationdatetime:155377824000000000
> > >
> > > TERM(9): _l_deactivationdatetime:155378687999969792
> > >
> > > TERM(10): _l_document_class:1
> > >
> > > TERM(11): _l_document_class:98305
> > >
> > > TERM(12): _l_folder:163841
> > >
> > > TERM(13): _l_folder:163843
> > >
> > > TERM(14): _l_hidden:aaa
> > >
> > > TERM(15): _l_last_modified_datetime:633427319866778624
> > >
> > > TERM(16): _l_last_modified_datetime:633427324812559872
> > >
> > > TERM(17): _l_last_modified_datetime:633760609388437504
> > >
> > > TERM(18): _l_meta:abc
> > >
> > > TERM(19): _l_meta:abc.ppt
> > >
> > > TERM(20): _l_meta:ddx
> > >
> > > TERM(21): _l_meta:doc
> > >
> > > TERM(22): _l_meta:xyz
> > >
> > > TERM(23): _l_meta:名
> > >
> > > TERM(24): _l_meta:問
> > >
> > > TERM(25): _l_meta:有
> > >
> > > TERM(26): _l_meta:檔
> > >
> > > TERM(27): _l_meta:測
> > >
> > > TERM(28): _l_meta:看
> > >
> > > TERM(29): _l_meta:試
> > >
> > > TERM(30): _l_meta:還
> > >
> > > TERM(31): _l_meta:題
> > >
> > > TERM(32): _l_parentdocument:196609
> > >
> > > TERM(33): _l_parentdocument:327681
> > >
> > > TERM(34): _l_parentdocument:557057
> > >
> > > TERM(35): _l_ratingavg:0
> > >
> > > TERM(36): _l_ratingmedian:0
> > >
> > > TERM(37): _l_ratingstdev:0
> > >
> > > TERM(38): _l_ratingsum:0
> > >
> > > TERM(39): _l_read_permission:admin
> > >
> > > TERM(40): _l_rootdocument:196609
> > >
> > > TERM(41): _l_rootdocument:327681
> > >
> > > TERM(42): _l_rootdocument:557057
> > >
> > > TERM(43): _l_state:0
> > >
> > > TERM(44): _l_state:2
> > >
> > > TERM(45): _l_summary:2123456789
> > >
> > > TERM(46): _l_summary:abc
> > >
> > > TERM(47): _l_summary:abc.ppt
> > >
> > > TERM(48): _l_summary:ddx
> > >
> > > TERM(49): _l_summary:doc
> > >
> > > TERM(50): _l_summary:xyz
> > >
> > > TERM(51): _l_summary:有
> > >
> > > TERM(52): _l_summary:還
> > >
> > > TERM(53): _l_title:123
> > >
> > > TERM(54): _l_title:class
> > >
> > > TERM(55): _l_title:default
> > >
> > > TERM(56): _l_title:document
> > >
> > > TERM(57): _l_title:名
> > >
> > > TERM(58): _l_title:問
> > >
> > > TERM(59): _l_title:檔
> > >
> > > TERM(60): _l_title:測
> > >
> > > TERM(61): _l_title:看
> > >
> > > TERM(62): _l_title:試
> > >
> > > TERM(63): _l_title:題
> > >
> > > TERM(64): _l_unique_key:196609
> > >
> > > TERM(65): _l_unique_key:327681
> > >
> > > TERM(66): _l_unique_key:557057
> > >
> > > TERM(67): _l_version:1
> > >
> > > TERM(68): 作者:123
> > >
> > > TERM(69): 摘要:2123456789
> > >
> > > TERM(70): 摘要:abc
> > >
> > > TERM(71): 摘要:abc.ppt
> > >
> > > TERM(72): 摘要:ddx
> > >
> > > TERM(73): 摘要:doc
> > >
> > > TERM(74): 摘要:xyz
> > >
> > > TERM(75): 摘要:有
> > >
> > > TERM(76): 摘要:還
> > >
> > > TERM(77): 標題:123
> > >
> > > TERM(78): 標題:class
> > >
> > > TERM(79): 標題:default
> > >
> > > TERM(80): 標題:document
> > >
> > > TERM(81): 標題:名
> > >
> > > TERM(82): 標題:問
> > >
> > > TERM(83): 標題:檔
> > >
> > > TERM(84): 標題:測
> > >
> > > TERM(85): 標題:看
> > >
> > > TERM(86): 標題:試
> > >
> > > TERM(87): 標題:題
> > >
> > > TERM(88): 關鍵詞:123
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > > And here is a sample code: read docs from original index and then write
> > to
> > > an new one.
> > >
> > >
> > >
> > > void CreateNewIndex(string OrgIndex)
> > >
> > > {
> > >
> > > IndexReader reader = IndexReader.Open(OrgIndex);
> > >
> > > IndexWriter writer = new IndexWriter("Floyd", new
> > > Lucene.Net.Analysis.WhitespaceAnalyzer(),true);
> > >
> > >
> > >
> > > for (int i = 0; i < reader.MaxDoc(); i++)
> > >
> > > {
> > >
> > > if (reader.IsDeleted(i) == true) continue;
> > >
> > >
> > >
> > > Lucene.Net.Documents.Document orgDoc =
> > reader.Document(i);
> > >
> > > System.Collections.IList fields = orgDoc.GetFields();
> > >
> > >
> > >
> > > Lucene.Net.Documents.Document newDoc = new Document();
> > >
> > > foreach (Lucene.Net.Documents.Field field in fields)
> > >
> > > {
> > >
> > > Lucene.Net.Documents.Field newField = new Field(
> > >
> > > System.Convert.ToBase64String(
> > > System.Text.Encoding.UTF8.GetBytes(field.Name())), //ç
> > >
> > > //field.Name(), //ç
> > >
> > > field.StringValue(),
> > >
> > > field.IsStored() ?
> > > Lucene.Net.Documents.Field.Store.YES :
> > Lucene.Net.Documents.Field.Store.NO<http://lucene.net.documents.field.store.no/>
> <
> > http://lucene.net.documents.field.store.no/>
> > > ,
> > >
> > > field.IsTokenized() ?
> > > Lucene.Net.Documents.Field.Index.TOKENIZED :
> > > Lucene.Net.Documents.Field.Index.UN_TOKENIZED);
> > >
> > >
> > >
> > > newDoc.Add(newField);
> > >
> > > }
> > >
> > > writer.AddDocument(newDoc);
> > >
> > > }
> > >
> > >
> > >
> > > writer.Close();
> > >
> > > reader.Close();
> > >
> > > }
> > >
> > >
> > >
> > >
> > >
> > > If some field names are chinese, then Luke returns “read past EOF”. But
> > if
> > > those field names are replaced with non-chinese names, then it works.
> > >
> > >
> > >
> > > DIGY
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > > -----Original Message-----
> > > From: Granroth, Neal V. [mailto:neal.granroth@thermofisher.com]
> > > Sent: Friday, April 24, 2009 8:53 PM
> > > To: lucene-net-dev@incubator.apache.org
> > > Subject: Luke-0.9.x cannot open index files
> > >
> > >
> > >
> > >
> > >
> > > Digy,
> > >
> > >
> > >
> > > Some additional information from the discussion on the lucene-net-user
> > list
> > > with Floyd Wu.
> > >
> > >
> > >
> > >
> > >
> > > I ran some further tests using Java Lucene 2.3.2 and JDK 1.5.
> > >
> > >
> > >
> > > The Java equivalents of the two small test applications I use to
> inspect
> > an
> > > index and compact it, function identically to the .NET versions (that
> > were
> > > built with VS2005 and Lucene.NET 2.3.1).
> > >
> > >
> > >
> > > That Luke cannot open the index appears to be a problem within Luke.
> > >
> > > Even if Floyd's index contains some odd entries, Java Lucene 2.3.2 does
> > not
> > > flag the index as corrupt; and both the Java and .NET versions report
> the
> > > same index content before and after the optimize operation.
> > >
> > >
> > >
> > >
> > >
> > > -- Neal
> > >
> > >
> > >
> > > -----Original Message-----
> > >
> > > From: Digy (JIRA) [mailto:jira@apache.org]
> > >
> > > Sent: Wednesday, April 08, 2009 6:28 PM
> > >
> > > To: lucene-net-dev@incubator.apache.org
> > >
> > > Subject: [jira] Commented: (LUCENENET-169) Changes to make Lucene.NET
> > > compatible with ASP.NET <http://asp.net/> <http://asp.net/> Medium
> Trust Level, in hosting
> > > environments (like GoDaddy...)
> > >
> > >
> > >
> > >
> > >
> > > [
> > >
> >
> https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12697335#action_12697335
> > ]
> > >
> > >
> > >
> > > Digy commented on LUCENENET-169:
> > >
> > > --------------------------------
> > >
> > >
> > >
> > > Although you can overcome all of them somehow;
> > >
> > >
> > >
> > > * controlling the the lifetime of IndexWriter/IndexReader in a
> naturally
> > > manner,
> > >
> > > * reopening the IndexReader only when needed using (for ex)
> > > FileSystemWatcher,
> > >
> > > * providing a separation between data & bussiness layer,
> > >
> > > * providing other apps an interface that may want to write its own user
> > > interface,
> > >
> > > * accessing a single search service from different web apps/from load
> > > balanced web servers
> > >
> > > * controlling the lifetime of searching/indexing code (without being
> > > effected by the restart of the IIS processes automatically when some
> > memory
> > > limit is exceeded (for ex.) )
> > >
> > > * Ability to access some system resources that can be restricted by IIS
> > >
> > > etc.
> > >
> > > make me think a separete search service is a better idea.But at last,
> it
> > is
> > > a design decision of you.
> > >
> > > (Think, A WebApp+Solr in Java world)
> > >
> > >
> > >
> > >
> > >
> > > DIGY
> > >
> > >
> > >
> > > > Changes to make Lucene.NET compatible with ASP.NET <http://asp.net/><
> http://asp.net/>
> > Medium Trust Level, in hosting environments (like GoDaddy...)
> > >
> > > >
> > >
> >
> -----------------------------------------------------------------------------------------------------------------
> > >
> > > >
> > >
> > > > Key: LUCENENET-169
> > >
> > > > URL:
> > https://issues.apache.org/jira/browse/LUCENENET-169
> > >
> > > > Project: Lucene.Net
> > >
> > > > Issue Type: Improvement
> > >
> > > > Environment: ASP.NET <http://asp.net/> <http://asp.net/>
> > >
> > > > Reporter: Corey Trager
> > >
> > > > Attachments: FSDirectory.patch
> > >
> > > >
> > >
> > > >
> > >
> > > > Microsoft has a configuration file for shared hosting for what they
> > call
> > > "Medium Trust". There are a couple places in FSDirectory.cs that
> > violate
> > > the restrictions of Medium Trust, but I coded workarounds, shown below.
> > >
> > > > #1)
> > >
> > > > // Corey Trager, Oct 2008: Commented call to GetTempPath to
> workaround
> > > permission restrictions at shared host.
> > >
> > > > // LOCK_DIR isn't used anyway.
> > >
> > > > public static readonly System.String LOCK_DIR = null; //
> > > SupportClass.AppSettings.Get("Lucene.Net.lockDir",
> > > System.IO.Path.GetTempPath());
> > >
> > > > #2)
> > >
> > > > /// <summary>Returns an array of strings, one for each
> > > Lucene index file in the directory. </summary>
> > >
> > > > public override System.String[] List()
> > >
> > > > {
> > >
> > > > /* Changes by Corey Trager, Oct 2008, to workaround permission
> > > restrictions at shared host */
> > >
> > > > System.IO.DirectoryInfo dir = new
> > > System.IO.DirectoryInfo(directory.FullName);
> > >
> > > > System.IO.FileInfo[] files = dir.GetFiles();
> > >
> > > > string[] list = new string[files.Length];
> > >
> > > > for (int i = 0; i < files.Length; i++)
> > >
> > > > {
> > >
> > > > list[i] = files[i].Name;
> > >
> > > > }
> > >
> > > > return list;
> > >
> > > > /* end of changes */
> > >
> > > > // System.String[] files =
> > > SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName,
> > > IndexFileNameFilter.GetFilter());
> > >
> > > > // for (int i = 0; i < files.Length; i++)
> > >
> > > > // {
> > >
> > > > // System.IO.FileInfo fi = new
> > > System.IO.FileInfo(files[i]);
> > >
> > > > // files[i] = fi.Name;
> > >
> > > > // }
> > >
> > > > // return files;
> > >
> > > > }
> > >
> > >
> > >
> > > --
> > >
> > > This message is automatically generated by JIRA.
> > >
> > > -
> > >
> > > You can reply to this email to add a comment to the issue online.
> > >
> > >
> >
>
RE: Luke-0.9.x cannot open index files
Posted by "Granroth, Neal V." <ne...@thermofisher.com>.
Floyd,
Here is a simple Java command-line application that displays the content of an index. It successfully opens your "documents" index using Java Lucene version 2.3.2 (the closest version to current Lucene.NET).
That this program works properly with your index, but Luke does not, shows that the problem is within Luke. You can provide this program with your index and bug report to the people supporting Luke.
-----------------------------------------------------------------
package app1;
import org.apache.lucene.index.*;
import org.apache.lucene.document.*;
public class Main
{
public Main() { }
public static void main(String[] args)
{
if (args.length > 0)
{
System.out.println("Index Folder: " + args[0]);
IndexReader ird = null;
try
{
ird = IndexReader.open( args[0] );
System.out.println("Index Version: " + ird.getVersion());
System.out.println(" isCurrent: " + ird.isCurrent() );
System.out.println(" isOptimized: " + ird.isOptimized());
System.out.println(" num Docs: " + ird.numDocs());
System.out.println(" max Docs: " + ird.maxDoc());
int numDOCs = ird.maxDoc();
if (numDOCs > 0)
{
for(int ii=0; ii<numDOCs; ++ii)
{
System.out.println("------------------------------------------");
System.out.println("Doc: " + ii );
System.out.println(" Deleted: " + ird.isDeleted(ii));
if ( !ird.isDeleted(ii) )
{
Document dx = ird.document(ii);
java.util.List fldList = dx.getFields();
int numFields = fldList.size();
for (int nn=0; nn<numFields; ++nn)
{
Field xf = (Field) fldList.get(nn);
String zname = xf.name();
boolean isStored = xf.isStored();
boolean isIndexed = xf.isIndexed();
String zvalue = xf.stringValue();
String scode = (isIndexed ? "I":"N") + "," + ( isStored ? "S":"U" );
if (zvalue != null)
System.out.println(" Field: " + zname + ", " + scode + ", Value: " + zvalue);
else
System.out.println(" Field: " + zname + ", " + scode + ", Value: (none)");
}
}
}
}
System.out.println("------------------------------------------");
System.out.println("Terms");
System.out.println("------------------------------------------");
TermEnum enuTRM = ird.terms();
while( enuTRM.next() )
{
int freq = enuTRM.docFreq();
Term oT = enuTRM.term();
if (oT != null)
{
System.out.println(" " + freq + ", " + oT.field() + ", \"" + oT.text() + "\"");
}
}
ird.close();
}
catch(Exception ex)
{
System.out.println("Open failed, exception: " + ex.toString() );
}
}
}
}
-----------------------------------------------------------------
-- Neal
-----Original Message-----
From: Floyd Wu [mailto:floyd.wu@gmail.com]
Sent: Monday, April 27, 2009 3:14 AM
To: lucene-net-dev@incubator.apache.org
Subject: Re: Luke-0.9.x cannot open index files
Thanks DIGY
So will you report this to Luke author or Java Lucene group?
I've been reported this situation to Luke author and he( or she) doesn't
think this is a bug of Luke.
floyd
2009/4/27 digy digy <di...@gmail.com>
> It is not a bug of Lucene.Net and as my sample code shows, Lucene.Net works
> well with chinese field names.
> I think, it is a bug in Luke.
>
> DIGY
>
>
>
> On Mon, Apr 27, 2009 at 8:49 AM, Floyd Wu <fl...@gmail.com> wrote:
>
> > Hi Digy,
> > Thanks for your help.
> > But if chinese field name is the problem, will it be "fix" in Lucene.Net
> or
> > how can I avoid this problem.
> >
> > Chinese field name is by design and probably not avoidable.
> >
> > Floyd
> >
> > 2009/4/25 Digy <di...@gmail.com>
> >
> > > I think, I found the bug. Here is the dump of the original index:
> > >
> > >
> > >
> > > NUMDOCS: 3
> > >
> > > MAXDOCS: 7
> > >
> > > DELETED(0): True
> > >
> > > DELETED(1): True
> > >
> > > DELETED(2): False
> > >
> > > DELETED(3): True
> > >
> > > DELETED(4): True
> > >
> > > DELETED(5): False
> > >
> > > DELETED(6): False
> > >
> > > TERM(0): _l_activationdatetime:552877632000000000
> > >
> > > TERM(1): _l_author:admin
> > >
> > > TERM(2): _l_bookmarkcount:0
> > >
> > > TERM(3): _l_clix:0
> > >
> > > TERM(4): _l_clix:1
> > >
> > > TERM(5): _l_creationdatetime:633427319866778624
> > >
> > > TERM(6): _l_creationdatetime:633427324812559872
> > >
> > > TERM(7): _l_creationdatetime:633760609388437504
> > >
> > > TERM(8): _l_deactivationdatetime:155377824000000000
> > >
> > > TERM(9): _l_deactivationdatetime:155378687999969792
> > >
> > > TERM(10): _l_document_class:1
> > >
> > > TERM(11): _l_document_class:98305
> > >
> > > TERM(12): _l_folder:163841
> > >
> > > TERM(13): _l_folder:163843
> > >
> > > TERM(14): _l_hidden:aaa
> > >
> > > TERM(15): _l_last_modified_datetime:633427319866778624
> > >
> > > TERM(16): _l_last_modified_datetime:633427324812559872
> > >
> > > TERM(17): _l_last_modified_datetime:633760609388437504
> > >
> > > TERM(18): _l_meta:abc
> > >
> > > TERM(19): _l_meta:abc.ppt
> > >
> > > TERM(20): _l_meta:ddx
> > >
> > > TERM(21): _l_meta:doc
> > >
> > > TERM(22): _l_meta:xyz
> > >
> > > TERM(23): _l_meta:名
> > >
> > > TERM(24): _l_meta:問
> > >
> > > TERM(25): _l_meta:有
> > >
> > > TERM(26): _l_meta:檔
> > >
> > > TERM(27): _l_meta:測
> > >
> > > TERM(28): _l_meta:看
> > >
> > > TERM(29): _l_meta:試
> > >
> > > TERM(30): _l_meta:還
> > >
> > > TERM(31): _l_meta:題
> > >
> > > TERM(32): _l_parentdocument:196609
> > >
> > > TERM(33): _l_parentdocument:327681
> > >
> > > TERM(34): _l_parentdocument:557057
> > >
> > > TERM(35): _l_ratingavg:0
> > >
> > > TERM(36): _l_ratingmedian:0
> > >
> > > TERM(37): _l_ratingstdev:0
> > >
> > > TERM(38): _l_ratingsum:0
> > >
> > > TERM(39): _l_read_permission:admin
> > >
> > > TERM(40): _l_rootdocument:196609
> > >
> > > TERM(41): _l_rootdocument:327681
> > >
> > > TERM(42): _l_rootdocument:557057
> > >
> > > TERM(43): _l_state:0
> > >
> > > TERM(44): _l_state:2
> > >
> > > TERM(45): _l_summary:2123456789
> > >
> > > TERM(46): _l_summary:abc
> > >
> > > TERM(47): _l_summary:abc.ppt
> > >
> > > TERM(48): _l_summary:ddx
> > >
> > > TERM(49): _l_summary:doc
> > >
> > > TERM(50): _l_summary:xyz
> > >
> > > TERM(51): _l_summary:有
> > >
> > > TERM(52): _l_summary:還
> > >
> > > TERM(53): _l_title:123
> > >
> > > TERM(54): _l_title:class
> > >
> > > TERM(55): _l_title:default
> > >
> > > TERM(56): _l_title:document
> > >
> > > TERM(57): _l_title:名
> > >
> > > TERM(58): _l_title:問
> > >
> > > TERM(59): _l_title:檔
> > >
> > > TERM(60): _l_title:測
> > >
> > > TERM(61): _l_title:看
> > >
> > > TERM(62): _l_title:試
> > >
> > > TERM(63): _l_title:題
> > >
> > > TERM(64): _l_unique_key:196609
> > >
> > > TERM(65): _l_unique_key:327681
> > >
> > > TERM(66): _l_unique_key:557057
> > >
> > > TERM(67): _l_version:1
> > >
> > > TERM(68): 作者:123
> > >
> > > TERM(69): 摘要:2123456789
> > >
> > > TERM(70): 摘要:abc
> > >
> > > TERM(71): 摘要:abc.ppt
> > >
> > > TERM(72): 摘要:ddx
> > >
> > > TERM(73): 摘要:doc
> > >
> > > TERM(74): 摘要:xyz
> > >
> > > TERM(75): 摘要:有
> > >
> > > TERM(76): 摘要:還
> > >
> > > TERM(77): 標題:123
> > >
> > > TERM(78): 標題:class
> > >
> > > TERM(79): 標題:default
> > >
> > > TERM(80): 標題:document
> > >
> > > TERM(81): 標題:名
> > >
> > > TERM(82): 標題:問
> > >
> > > TERM(83): 標題:檔
> > >
> > > TERM(84): 標題:測
> > >
> > > TERM(85): 標題:看
> > >
> > > TERM(86): 標題:試
> > >
> > > TERM(87): 標題:題
> > >
> > > TERM(88): 關鍵詞:123
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > > And here is a sample code: read docs from original index and then write
> > to
> > > an new one.
> > >
> > >
> > >
> > > void CreateNewIndex(string OrgIndex)
> > >
> > > {
> > >
> > > IndexReader reader = IndexReader.Open(OrgIndex);
> > >
> > > IndexWriter writer = new IndexWriter("Floyd", new
> > > Lucene.Net.Analysis.WhitespaceAnalyzer(),true);
> > >
> > >
> > >
> > > for (int i = 0; i < reader.MaxDoc(); i++)
> > >
> > > {
> > >
> > > if (reader.IsDeleted(i) == true) continue;
> > >
> > >
> > >
> > > Lucene.Net.Documents.Document orgDoc =
> > reader.Document(i);
> > >
> > > System.Collections.IList fields = orgDoc.GetFields();
> > >
> > >
> > >
> > > Lucene.Net.Documents.Document newDoc = new Document();
> > >
> > > foreach (Lucene.Net.Documents.Field field in fields)
> > >
> > > {
> > >
> > > Lucene.Net.Documents.Field newField = new Field(
> > >
> > > System.Convert.ToBase64String(
> > > System.Text.Encoding.UTF8.GetBytes(field.Name())), //ç
> > >
> > > //field.Name(), //ç
> > >
> > > field.StringValue(),
> > >
> > > field.IsStored() ?
> > > Lucene.Net.Documents.Field.Store.YES :
> > Lucene.Net.Documents.Field.Store.NO<http://lucene.net.documents.field.store.no/>
> <
> > http://lucene.net.documents.field.store.no/>
> > > ,
> > >
> > > field.IsTokenized() ?
> > > Lucene.Net.Documents.Field.Index.TOKENIZED :
> > > Lucene.Net.Documents.Field.Index.UN_TOKENIZED);
> > >
> > >
> > >
> > > newDoc.Add(newField);
> > >
> > > }
> > >
> > > writer.AddDocument(newDoc);
> > >
> > > }
> > >
> > >
> > >
> > > writer.Close();
> > >
> > > reader.Close();
> > >
> > > }
> > >
> > >
> > >
> > >
> > >
> > > If some field names are chinese, then Luke returns “read past EOF”. But
> > if
> > > those field names are replaced with non-chinese names, then it works.
> > >
> > >
> > >
> > > DIGY
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > > -----Original Message-----
> > > From: Granroth, Neal V. [mailto:neal.granroth@thermofisher.com]
> > > Sent: Friday, April 24, 2009 8:53 PM
> > > To: lucene-net-dev@incubator.apache.org
> > > Subject: Luke-0.9.x cannot open index files
> > >
> > >
> > >
> > >
> > >
> > > Digy,
> > >
> > >
> > >
> > > Some additional information from the discussion on the lucene-net-user
> > list
> > > with Floyd Wu.
> > >
> > >
> > >
> > >
> > >
> > > I ran some further tests using Java Lucene 2.3.2 and JDK 1.5.
> > >
> > >
> > >
> > > The Java equivalents of the two small test applications I use to
> inspect
> > an
> > > index and compact it, function identically to the .NET versions (that
> > were
> > > built with VS2005 and Lucene.NET 2.3.1).
> > >
> > >
> > >
> > > That Luke cannot open the index appears to be a problem within Luke.
> > >
> > > Even if Floyd's index contains some odd entries, Java Lucene 2.3.2 does
> > not
> > > flag the index as corrupt; and both the Java and .NET versions report
> the
> > > same index content before and after the optimize operation.
> > >
> > >
> > >
> > >
> > >
> > > -- Neal
> > >
> > >
> > >
> > > -----Original Message-----
> > >
> > > From: Digy (JIRA) [mailto:jira@apache.org]
> > >
> > > Sent: Wednesday, April 08, 2009 6:28 PM
> > >
> > > To: lucene-net-dev@incubator.apache.org
> > >
> > > Subject: [jira] Commented: (LUCENENET-169) Changes to make Lucene.NET
> > > compatible with ASP.NET <http://asp.net/> <http://asp.net/> Medium
> Trust Level, in hosting
> > > environments (like GoDaddy...)
> > >
> > >
> > >
> > >
> > >
> > > [
> > >
> >
> https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12697335#action_12697335
> > ]
> > >
> > >
> > >
> > > Digy commented on LUCENENET-169:
> > >
> > > --------------------------------
> > >
> > >
> > >
> > > Although you can overcome all of them somehow;
> > >
> > >
> > >
> > > * controlling the the lifetime of IndexWriter/IndexReader in a
> naturally
> > > manner,
> > >
> > > * reopening the IndexReader only when needed using (for ex)
> > > FileSystemWatcher,
> > >
> > > * providing a separation between data & bussiness layer,
> > >
> > > * providing other apps an interface that may want to write its own user
> > > interface,
> > >
> > > * accessing a single search service from different web apps/from load
> > > balanced web servers
> > >
> > > * controlling the lifetime of searching/indexing code (without being
> > > effected by the restart of the IIS processes automatically when some
> > memory
> > > limit is exceeded (for ex.) )
> > >
> > > * Ability to access some system resources that can be restricted by IIS
> > >
> > > etc.
> > >
> > > make me think a separete search service is a better idea.But at last,
> it
> > is
> > > a design decision of you.
> > >
> > > (Think, A WebApp+Solr in Java world)
> > >
> > >
> > >
> > >
> > >
> > > DIGY
> > >
> > >
> > >
> > > > Changes to make Lucene.NET compatible with ASP.NET <http://asp.net/><
> http://asp.net/>
> > Medium Trust Level, in hosting environments (like GoDaddy...)
> > >
> > > >
> > >
> >
> -----------------------------------------------------------------------------------------------------------------
> > >
> > > >
> > >
> > > > Key: LUCENENET-169
> > >
> > > > URL:
> > https://issues.apache.org/jira/browse/LUCENENET-169
> > >
> > > > Project: Lucene.Net
> > >
> > > > Issue Type: Improvement
> > >
> > > > Environment: ASP.NET <http://asp.net/> <http://asp.net/>
> > >
> > > > Reporter: Corey Trager
> > >
> > > > Attachments: FSDirectory.patch
> > >
> > > >
> > >
> > > >
> > >
> > > > Microsoft has a configuration file for shared hosting for what they
> > call
> > > "Medium Trust". There are a couple places in FSDirectory.cs that
> > violate
> > > the restrictions of Medium Trust, but I coded workarounds, shown below.
> > >
> > > > #1)
> > >
> > > > // Corey Trager, Oct 2008: Commented call to GetTempPath to
> workaround
> > > permission restrictions at shared host.
> > >
> > > > // LOCK_DIR isn't used anyway.
> > >
> > > > public static readonly System.String LOCK_DIR = null; //
> > > SupportClass.AppSettings.Get("Lucene.Net.lockDir",
> > > System.IO.Path.GetTempPath());
> > >
> > > > #2)
> > >
> > > > /// <summary>Returns an array of strings, one for each
> > > Lucene index file in the directory. </summary>
> > >
> > > > public override System.String[] List()
> > >
> > > > {
> > >
> > > > /* Changes by Corey Trager, Oct 2008, to workaround permission
> > > restrictions at shared host */
> > >
> > > > System.IO.DirectoryInfo dir = new
> > > System.IO.DirectoryInfo(directory.FullName);
> > >
> > > > System.IO.FileInfo[] files = dir.GetFiles();
> > >
> > > > string[] list = new string[files.Length];
> > >
> > > > for (int i = 0; i < files.Length; i++)
> > >
> > > > {
> > >
> > > > list[i] = files[i].Name;
> > >
> > > > }
> > >
> > > > return list;
> > >
> > > > /* end of changes */
> > >
> > > > // System.String[] files =
> > > SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName,
> > > IndexFileNameFilter.GetFilter());
> > >
> > > > // for (int i = 0; i < files.Length; i++)
> > >
> > > > // {
> > >
> > > > // System.IO.FileInfo fi = new
> > > System.IO.FileInfo(files[i]);
> > >
> > > > // files[i] = fi.Name;
> > >
> > > > // }
> > >
> > > > // return files;
> > >
> > > > }
> > >
> > >
> > >
> > > --
> > >
> > > This message is automatically generated by JIRA.
> > >
> > > -
> > >
> > > You can reply to this email to add a comment to the issue online.
> > >
> > >
> >
>
Re: Luke-0.9.x cannot open index files
Posted by Floyd Wu <fl...@gmail.com>.
Thanks DIGY
So will you report this to Luke author or Java Lucene group?
I've been reported this situation to Luke author and he( or she) doesn't
think this is a bug of Luke.
floyd
2009/4/27 digy digy <di...@gmail.com>
> It is not a bug of Lucene.Net and as my sample code shows, Lucene.Net works
> well with chinese field names.
> I think, it is a bug in Luke.
>
> DIGY
>
>
>
> On Mon, Apr 27, 2009 at 8:49 AM, Floyd Wu <fl...@gmail.com> wrote:
>
> > Hi Digy,
> > Thanks for your help.
> > But if chinese field name is the problem, will it be "fix" in Lucene.Net
> or
> > how can I avoid this problem.
> >
> > Chinese field name is by design and probably not avoidable.
> >
> > Floyd
> >
> > 2009/4/25 Digy <di...@gmail.com>
> >
> > > I think, I found the bug. Here is the dump of the original index:
> > >
> > >
> > >
> > > NUMDOCS: 3
> > >
> > > MAXDOCS: 7
> > >
> > > DELETED(0): True
> > >
> > > DELETED(1): True
> > >
> > > DELETED(2): False
> > >
> > > DELETED(3): True
> > >
> > > DELETED(4): True
> > >
> > > DELETED(5): False
> > >
> > > DELETED(6): False
> > >
> > > TERM(0): _l_activationdatetime:552877632000000000
> > >
> > > TERM(1): _l_author:admin
> > >
> > > TERM(2): _l_bookmarkcount:0
> > >
> > > TERM(3): _l_clix:0
> > >
> > > TERM(4): _l_clix:1
> > >
> > > TERM(5): _l_creationdatetime:633427319866778624
> > >
> > > TERM(6): _l_creationdatetime:633427324812559872
> > >
> > > TERM(7): _l_creationdatetime:633760609388437504
> > >
> > > TERM(8): _l_deactivationdatetime:155377824000000000
> > >
> > > TERM(9): _l_deactivationdatetime:155378687999969792
> > >
> > > TERM(10): _l_document_class:1
> > >
> > > TERM(11): _l_document_class:98305
> > >
> > > TERM(12): _l_folder:163841
> > >
> > > TERM(13): _l_folder:163843
> > >
> > > TERM(14): _l_hidden:aaa
> > >
> > > TERM(15): _l_last_modified_datetime:633427319866778624
> > >
> > > TERM(16): _l_last_modified_datetime:633427324812559872
> > >
> > > TERM(17): _l_last_modified_datetime:633760609388437504
> > >
> > > TERM(18): _l_meta:abc
> > >
> > > TERM(19): _l_meta:abc.ppt
> > >
> > > TERM(20): _l_meta:ddx
> > >
> > > TERM(21): _l_meta:doc
> > >
> > > TERM(22): _l_meta:xyz
> > >
> > > TERM(23): _l_meta:名
> > >
> > > TERM(24): _l_meta:問
> > >
> > > TERM(25): _l_meta:有
> > >
> > > TERM(26): _l_meta:檔
> > >
> > > TERM(27): _l_meta:測
> > >
> > > TERM(28): _l_meta:看
> > >
> > > TERM(29): _l_meta:試
> > >
> > > TERM(30): _l_meta:還
> > >
> > > TERM(31): _l_meta:題
> > >
> > > TERM(32): _l_parentdocument:196609
> > >
> > > TERM(33): _l_parentdocument:327681
> > >
> > > TERM(34): _l_parentdocument:557057
> > >
> > > TERM(35): _l_ratingavg:0
> > >
> > > TERM(36): _l_ratingmedian:0
> > >
> > > TERM(37): _l_ratingstdev:0
> > >
> > > TERM(38): _l_ratingsum:0
> > >
> > > TERM(39): _l_read_permission:admin
> > >
> > > TERM(40): _l_rootdocument:196609
> > >
> > > TERM(41): _l_rootdocument:327681
> > >
> > > TERM(42): _l_rootdocument:557057
> > >
> > > TERM(43): _l_state:0
> > >
> > > TERM(44): _l_state:2
> > >
> > > TERM(45): _l_summary:2123456789
> > >
> > > TERM(46): _l_summary:abc
> > >
> > > TERM(47): _l_summary:abc.ppt
> > >
> > > TERM(48): _l_summary:ddx
> > >
> > > TERM(49): _l_summary:doc
> > >
> > > TERM(50): _l_summary:xyz
> > >
> > > TERM(51): _l_summary:有
> > >
> > > TERM(52): _l_summary:還
> > >
> > > TERM(53): _l_title:123
> > >
> > > TERM(54): _l_title:class
> > >
> > > TERM(55): _l_title:default
> > >
> > > TERM(56): _l_title:document
> > >
> > > TERM(57): _l_title:名
> > >
> > > TERM(58): _l_title:問
> > >
> > > TERM(59): _l_title:檔
> > >
> > > TERM(60): _l_title:測
> > >
> > > TERM(61): _l_title:看
> > >
> > > TERM(62): _l_title:試
> > >
> > > TERM(63): _l_title:題
> > >
> > > TERM(64): _l_unique_key:196609
> > >
> > > TERM(65): _l_unique_key:327681
> > >
> > > TERM(66): _l_unique_key:557057
> > >
> > > TERM(67): _l_version:1
> > >
> > > TERM(68): 作者:123
> > >
> > > TERM(69): 摘要:2123456789
> > >
> > > TERM(70): 摘要:abc
> > >
> > > TERM(71): 摘要:abc.ppt
> > >
> > > TERM(72): 摘要:ddx
> > >
> > > TERM(73): 摘要:doc
> > >
> > > TERM(74): 摘要:xyz
> > >
> > > TERM(75): 摘要:有
> > >
> > > TERM(76): 摘要:還
> > >
> > > TERM(77): 標題:123
> > >
> > > TERM(78): 標題:class
> > >
> > > TERM(79): 標題:default
> > >
> > > TERM(80): 標題:document
> > >
> > > TERM(81): 標題:名
> > >
> > > TERM(82): 標題:問
> > >
> > > TERM(83): 標題:檔
> > >
> > > TERM(84): 標題:測
> > >
> > > TERM(85): 標題:看
> > >
> > > TERM(86): 標題:試
> > >
> > > TERM(87): 標題:題
> > >
> > > TERM(88): 關鍵詞:123
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > > And here is a sample code: read docs from original index and then write
> > to
> > > an new one.
> > >
> > >
> > >
> > > void CreateNewIndex(string OrgIndex)
> > >
> > > {
> > >
> > > IndexReader reader = IndexReader.Open(OrgIndex);
> > >
> > > IndexWriter writer = new IndexWriter("Floyd", new
> > > Lucene.Net.Analysis.WhitespaceAnalyzer(),true);
> > >
> > >
> > >
> > > for (int i = 0; i < reader.MaxDoc(); i++)
> > >
> > > {
> > >
> > > if (reader.IsDeleted(i) == true) continue;
> > >
> > >
> > >
> > > Lucene.Net.Documents.Document orgDoc =
> > reader.Document(i);
> > >
> > > System.Collections.IList fields = orgDoc.GetFields();
> > >
> > >
> > >
> > > Lucene.Net.Documents.Document newDoc = new Document();
> > >
> > > foreach (Lucene.Net.Documents.Field field in fields)
> > >
> > > {
> > >
> > > Lucene.Net.Documents.Field newField = new Field(
> > >
> > > System.Convert.ToBase64String(
> > > System.Text.Encoding.UTF8.GetBytes(field.Name())), //ç
> > >
> > > //field.Name(), //ç
> > >
> > > field.StringValue(),
> > >
> > > field.IsStored() ?
> > > Lucene.Net.Documents.Field.Store.YES :
> > Lucene.Net.Documents.Field.Store.NO<http://lucene.net.documents.field.store.no/>
> <
> > http://lucene.net.documents.field.store.no/>
> > > ,
> > >
> > > field.IsTokenized() ?
> > > Lucene.Net.Documents.Field.Index.TOKENIZED :
> > > Lucene.Net.Documents.Field.Index.UN_TOKENIZED);
> > >
> > >
> > >
> > > newDoc.Add(newField);
> > >
> > > }
> > >
> > > writer.AddDocument(newDoc);
> > >
> > > }
> > >
> > >
> > >
> > > writer.Close();
> > >
> > > reader.Close();
> > >
> > > }
> > >
> > >
> > >
> > >
> > >
> > > If some field names are chinese, then Luke returns “read past EOF”. But
> > if
> > > those field names are replaced with non-chinese names, then it works.
> > >
> > >
> > >
> > > DIGY
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > > -----Original Message-----
> > > From: Granroth, Neal V. [mailto:neal.granroth@thermofisher.com]
> > > Sent: Friday, April 24, 2009 8:53 PM
> > > To: lucene-net-dev@incubator.apache.org
> > > Subject: Luke-0.9.x cannot open index files
> > >
> > >
> > >
> > >
> > >
> > > Digy,
> > >
> > >
> > >
> > > Some additional information from the discussion on the lucene-net-user
> > list
> > > with Floyd Wu.
> > >
> > >
> > >
> > >
> > >
> > > I ran some further tests using Java Lucene 2.3.2 and JDK 1.5.
> > >
> > >
> > >
> > > The Java equivalents of the two small test applications I use to
> inspect
> > an
> > > index and compact it, function identically to the .NET versions (that
> > were
> > > built with VS2005 and Lucene.NET 2.3.1).
> > >
> > >
> > >
> > > That Luke cannot open the index appears to be a problem within Luke.
> > >
> > > Even if Floyd's index contains some odd entries, Java Lucene 2.3.2 does
> > not
> > > flag the index as corrupt; and both the Java and .NET versions report
> the
> > > same index content before and after the optimize operation.
> > >
> > >
> > >
> > >
> > >
> > > -- Neal
> > >
> > >
> > >
> > > **************************************************************
> > >
> > > Neal Granroth
> > >
> > > Software Engineer, Molecular Spectroscopy
> > >
> > > Thermo Fisher Scientific
> > >
> > > 5225 Verona Road, Madison, WI 53711
> > >
> > >
> > >
> > > neal.granroth@thermofisher.com
> > >
> > > Tel: 608-276-5645
> > >
> > > Fax: 608-276-6328
> > >
> > >
> > >
> > > www.thermofisher.com
> > >
> > >
> > >
> > > WORLDWIDE CONFIDENTIALITY NOTE: Dissemination, distribution or copying
> of
> > > this e-mail or the information herein by anyone other than the intended
> > > recipient, or an employee or agent of a system responsible for
> delivering
> > > the message to the intended recipient, is prohibited. If you are not
> the
> > > intended recipient, please inform the sender and delete all copies.
> > >
> > >
> > >
> > > -----Original Message-----
> > >
> > > From: Digy (JIRA) [mailto:jira@apache.org]
> > >
> > > Sent: Wednesday, April 08, 2009 6:28 PM
> > >
> > > To: lucene-net-dev@incubator.apache.org
> > >
> > > Subject: [jira] Commented: (LUCENENET-169) Changes to make Lucene.NET
> > > compatible with ASP.NET <http://asp.net/> <http://asp.net/> Medium
> Trust Level, in hosting
> > > environments (like GoDaddy...)
> > >
> > >
> > >
> > >
> > >
> > > [
> > >
> >
> https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12697335#action_12697335
> > ]
> > >
> > >
> > >
> > > Digy commented on LUCENENET-169:
> > >
> > > --------------------------------
> > >
> > >
> > >
> > > Although you can overcome all of them somehow;
> > >
> > >
> > >
> > > * controlling the the lifetime of IndexWriter/IndexReader in a
> naturally
> > > manner,
> > >
> > > * reopening the IndexReader only when needed using (for ex)
> > > FileSystemWatcher,
> > >
> > > * providing a separation between data & bussiness layer,
> > >
> > > * providing other apps an interface that may want to write its own user
> > > interface,
> > >
> > > * accessing a single search service from different web apps/from load
> > > balanced web servers
> > >
> > > * controlling the lifetime of searching/indexing code (without being
> > > effected by the restart of the IIS processes automatically when some
> > memory
> > > limit is exceeded (for ex.) )
> > >
> > > * Ability to access some system resources that can be restricted by IIS
> > >
> > > etc.
> > >
> > > make me think a separete search service is a better idea.But at last,
> it
> > is
> > > a design decision of you.
> > >
> > > (Think, A WebApp+Solr in Java world)
> > >
> > >
> > >
> > >
> > >
> > > DIGY
> > >
> > >
> > >
> > > > Changes to make Lucene.NET compatible with ASP.NET <http://asp.net/><
> http://asp.net/>
> > Medium Trust Level, in hosting environments (like GoDaddy...)
> > >
> > > >
> > >
> >
> -----------------------------------------------------------------------------------------------------------------
> > >
> > > >
> > >
> > > > Key: LUCENENET-169
> > >
> > > > URL:
> > https://issues.apache.org/jira/browse/LUCENENET-169
> > >
> > > > Project: Lucene.Net
> > >
> > > > Issue Type: Improvement
> > >
> > > > Environment: ASP.NET <http://asp.net/> <http://asp.net/>
> > >
> > > > Reporter: Corey Trager
> > >
> > > > Attachments: FSDirectory.patch
> > >
> > > >
> > >
> > > >
> > >
> > > > Microsoft has a configuration file for shared hosting for what they
> > call
> > > "Medium Trust". There are a couple places in FSDirectory.cs that
> > violate
> > > the restrictions of Medium Trust, but I coded workarounds, shown below.
> > >
> > > > #1)
> > >
> > > > // Corey Trager, Oct 2008: Commented call to GetTempPath to
> workaround
> > > permission restrictions at shared host.
> > >
> > > > // LOCK_DIR isn't used anyway.
> > >
> > > > public static readonly System.String LOCK_DIR = null; //
> > > SupportClass.AppSettings.Get("Lucene.Net.lockDir",
> > > System.IO.Path.GetTempPath());
> > >
> > > > #2)
> > >
> > > > /// <summary>Returns an array of strings, one for each
> > > Lucene index file in the directory. </summary>
> > >
> > > > public override System.String[] List()
> > >
> > > > {
> > >
> > > > /* Changes by Corey Trager, Oct 2008, to workaround permission
> > > restrictions at shared host */
> > >
> > > > System.IO.DirectoryInfo dir = new
> > > System.IO.DirectoryInfo(directory.FullName);
> > >
> > > > System.IO.FileInfo[] files = dir.GetFiles();
> > >
> > > > string[] list = new string[files.Length];
> > >
> > > > for (int i = 0; i < files.Length; i++)
> > >
> > > > {
> > >
> > > > list[i] = files[i].Name;
> > >
> > > > }
> > >
> > > > return list;
> > >
> > > > /* end of changes */
> > >
> > > > // System.String[] files =
> > > SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName,
> > > IndexFileNameFilter.GetFilter());
> > >
> > > > // for (int i = 0; i < files.Length; i++)
> > >
> > > > // {
> > >
> > > > // System.IO.FileInfo fi = new
> > > System.IO.FileInfo(files[i]);
> > >
> > > > // files[i] = fi.Name;
> > >
> > > > // }
> > >
> > > > // return files;
> > >
> > > > }
> > >
> > >
> > >
> > > --
> > >
> > > This message is automatically generated by JIRA.
> > >
> > > -
> > >
> > > You can reply to this email to add a comment to the issue online.
> > >
> > >
> >
>
Re: Luke-0.9.x cannot open index files
Posted by digy digy <di...@gmail.com>.
It is not a bug of Lucene.Net and as my sample code shows, Lucene.Net works
well with chinese field names.
I think, it is a bug in Luke.
DIGY
On Mon, Apr 27, 2009 at 8:49 AM, Floyd Wu <fl...@gmail.com> wrote:
> Hi Digy,
> Thanks for your help.
> But if chinese field name is the problem, will it be "fix" in Lucene.Net or
> how can I avoid this problem.
>
> Chinese field name is by design and probably not avoidable.
>
> Floyd
>
> 2009/4/25 Digy <di...@gmail.com>
>
> > I think, I found the bug. Here is the dump of the original index:
> >
> >
> >
> > NUMDOCS: 3
> >
> > MAXDOCS: 7
> >
> > DELETED(0): True
> >
> > DELETED(1): True
> >
> > DELETED(2): False
> >
> > DELETED(3): True
> >
> > DELETED(4): True
> >
> > DELETED(5): False
> >
> > DELETED(6): False
> >
> > TERM(0): _l_activationdatetime:552877632000000000
> >
> > TERM(1): _l_author:admin
> >
> > TERM(2): _l_bookmarkcount:0
> >
> > TERM(3): _l_clix:0
> >
> > TERM(4): _l_clix:1
> >
> > TERM(5): _l_creationdatetime:633427319866778624
> >
> > TERM(6): _l_creationdatetime:633427324812559872
> >
> > TERM(7): _l_creationdatetime:633760609388437504
> >
> > TERM(8): _l_deactivationdatetime:155377824000000000
> >
> > TERM(9): _l_deactivationdatetime:155378687999969792
> >
> > TERM(10): _l_document_class:1
> >
> > TERM(11): _l_document_class:98305
> >
> > TERM(12): _l_folder:163841
> >
> > TERM(13): _l_folder:163843
> >
> > TERM(14): _l_hidden:aaa
> >
> > TERM(15): _l_last_modified_datetime:633427319866778624
> >
> > TERM(16): _l_last_modified_datetime:633427324812559872
> >
> > TERM(17): _l_last_modified_datetime:633760609388437504
> >
> > TERM(18): _l_meta:abc
> >
> > TERM(19): _l_meta:abc.ppt
> >
> > TERM(20): _l_meta:ddx
> >
> > TERM(21): _l_meta:doc
> >
> > TERM(22): _l_meta:xyz
> >
> > TERM(23): _l_meta:名
> >
> > TERM(24): _l_meta:問
> >
> > TERM(25): _l_meta:有
> >
> > TERM(26): _l_meta:檔
> >
> > TERM(27): _l_meta:測
> >
> > TERM(28): _l_meta:看
> >
> > TERM(29): _l_meta:試
> >
> > TERM(30): _l_meta:還
> >
> > TERM(31): _l_meta:題
> >
> > TERM(32): _l_parentdocument:196609
> >
> > TERM(33): _l_parentdocument:327681
> >
> > TERM(34): _l_parentdocument:557057
> >
> > TERM(35): _l_ratingavg:0
> >
> > TERM(36): _l_ratingmedian:0
> >
> > TERM(37): _l_ratingstdev:0
> >
> > TERM(38): _l_ratingsum:0
> >
> > TERM(39): _l_read_permission:admin
> >
> > TERM(40): _l_rootdocument:196609
> >
> > TERM(41): _l_rootdocument:327681
> >
> > TERM(42): _l_rootdocument:557057
> >
> > TERM(43): _l_state:0
> >
> > TERM(44): _l_state:2
> >
> > TERM(45): _l_summary:2123456789
> >
> > TERM(46): _l_summary:abc
> >
> > TERM(47): _l_summary:abc.ppt
> >
> > TERM(48): _l_summary:ddx
> >
> > TERM(49): _l_summary:doc
> >
> > TERM(50): _l_summary:xyz
> >
> > TERM(51): _l_summary:有
> >
> > TERM(52): _l_summary:還
> >
> > TERM(53): _l_title:123
> >
> > TERM(54): _l_title:class
> >
> > TERM(55): _l_title:default
> >
> > TERM(56): _l_title:document
> >
> > TERM(57): _l_title:名
> >
> > TERM(58): _l_title:問
> >
> > TERM(59): _l_title:檔
> >
> > TERM(60): _l_title:測
> >
> > TERM(61): _l_title:看
> >
> > TERM(62): _l_title:試
> >
> > TERM(63): _l_title:題
> >
> > TERM(64): _l_unique_key:196609
> >
> > TERM(65): _l_unique_key:327681
> >
> > TERM(66): _l_unique_key:557057
> >
> > TERM(67): _l_version:1
> >
> > TERM(68): 作者:123
> >
> > TERM(69): 摘要:2123456789
> >
> > TERM(70): 摘要:abc
> >
> > TERM(71): 摘要:abc.ppt
> >
> > TERM(72): 摘要:ddx
> >
> > TERM(73): 摘要:doc
> >
> > TERM(74): 摘要:xyz
> >
> > TERM(75): 摘要:有
> >
> > TERM(76): 摘要:還
> >
> > TERM(77): 標題:123
> >
> > TERM(78): 標題:class
> >
> > TERM(79): 標題:default
> >
> > TERM(80): 標題:document
> >
> > TERM(81): 標題:名
> >
> > TERM(82): 標題:問
> >
> > TERM(83): 標題:檔
> >
> > TERM(84): 標題:測
> >
> > TERM(85): 標題:看
> >
> > TERM(86): 標題:試
> >
> > TERM(87): 標題:題
> >
> > TERM(88): 關鍵詞:123
> >
> >
> >
> >
> >
> >
> >
> > And here is a sample code: read docs from original index and then write
> to
> > an new one.
> >
> >
> >
> > void CreateNewIndex(string OrgIndex)
> >
> > {
> >
> > IndexReader reader = IndexReader.Open(OrgIndex);
> >
> > IndexWriter writer = new IndexWriter("Floyd", new
> > Lucene.Net.Analysis.WhitespaceAnalyzer(),true);
> >
> >
> >
> > for (int i = 0; i < reader.MaxDoc(); i++)
> >
> > {
> >
> > if (reader.IsDeleted(i) == true) continue;
> >
> >
> >
> > Lucene.Net.Documents.Document orgDoc =
> reader.Document(i);
> >
> > System.Collections.IList fields = orgDoc.GetFields();
> >
> >
> >
> > Lucene.Net.Documents.Document newDoc = new Document();
> >
> > foreach (Lucene.Net.Documents.Field field in fields)
> >
> > {
> >
> > Lucene.Net.Documents.Field newField = new Field(
> >
> > System.Convert.ToBase64String(
> > System.Text.Encoding.UTF8.GetBytes(field.Name())), //ç
> >
> > //field.Name(), //ç
> >
> > field.StringValue(),
> >
> > field.IsStored() ?
> > Lucene.Net.Documents.Field.Store.YES :
> Lucene.Net.Documents.Field.Store.NO<
> http://lucene.net.documents.field.store.no/>
> > ,
> >
> > field.IsTokenized() ?
> > Lucene.Net.Documents.Field.Index.TOKENIZED :
> > Lucene.Net.Documents.Field.Index.UN_TOKENIZED);
> >
> >
> >
> > newDoc.Add(newField);
> >
> > }
> >
> > writer.AddDocument(newDoc);
> >
> > }
> >
> >
> >
> > writer.Close();
> >
> > reader.Close();
> >
> > }
> >
> >
> >
> >
> >
> > If some field names are chinese, then Luke returns “read past EOF”. But
> if
> > those field names are replaced with non-chinese names, then it works.
> >
> >
> >
> > DIGY
> >
> >
> >
> >
> >
> >
> >
> >
> >
> >
> >
> > -----Original Message-----
> > From: Granroth, Neal V. [mailto:neal.granroth@thermofisher.com]
> > Sent: Friday, April 24, 2009 8:53 PM
> > To: lucene-net-dev@incubator.apache.org
> > Subject: Luke-0.9.x cannot open index files
> >
> >
> >
> >
> >
> > Digy,
> >
> >
> >
> > Some additional information from the discussion on the lucene-net-user
> list
> > with Floyd Wu.
> >
> >
> >
> >
> >
> > I ran some further tests using Java Lucene 2.3.2 and JDK 1.5.
> >
> >
> >
> > The Java equivalents of the two small test applications I use to inspect
> an
> > index and compact it, function identically to the .NET versions (that
> were
> > built with VS2005 and Lucene.NET 2.3.1).
> >
> >
> >
> > That Luke cannot open the index appears to be a problem within Luke.
> >
> > Even if Floyd's index contains some odd entries, Java Lucene 2.3.2 does
> not
> > flag the index as corrupt; and both the Java and .NET versions report the
> > same index content before and after the optimize operation.
> >
> >
> >
> >
> >
> > -- Neal
> >
> >
> >
> > **************************************************************
> >
> > Neal Granroth
> >
> > Software Engineer, Molecular Spectroscopy
> >
> > Thermo Fisher Scientific
> >
> > 5225 Verona Road, Madison, WI 53711
> >
> >
> >
> > neal.granroth@thermofisher.com
> >
> > Tel: 608-276-5645
> >
> > Fax: 608-276-6328
> >
> >
> >
> > www.thermofisher.com
> >
> >
> >
> > WORLDWIDE CONFIDENTIALITY NOTE: Dissemination, distribution or copying of
> > this e-mail or the information herein by anyone other than the intended
> > recipient, or an employee or agent of a system responsible for delivering
> > the message to the intended recipient, is prohibited. If you are not the
> > intended recipient, please inform the sender and delete all copies.
> >
> >
> >
> > -----Original Message-----
> >
> > From: Digy (JIRA) [mailto:jira@apache.org]
> >
> > Sent: Wednesday, April 08, 2009 6:28 PM
> >
> > To: lucene-net-dev@incubator.apache.org
> >
> > Subject: [jira] Commented: (LUCENENET-169) Changes to make Lucene.NET
> > compatible with ASP.NET <http://asp.net/> Medium Trust Level, in hosting
> > environments (like GoDaddy...)
> >
> >
> >
> >
> >
> > [
> >
> https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12697335#action_12697335
> ]
> >
> >
> >
> > Digy commented on LUCENENET-169:
> >
> > --------------------------------
> >
> >
> >
> > Although you can overcome all of them somehow;
> >
> >
> >
> > * controlling the the lifetime of IndexWriter/IndexReader in a naturally
> > manner,
> >
> > * reopening the IndexReader only when needed using (for ex)
> > FileSystemWatcher,
> >
> > * providing a separation between data & bussiness layer,
> >
> > * providing other apps an interface that may want to write its own user
> > interface,
> >
> > * accessing a single search service from different web apps/from load
> > balanced web servers
> >
> > * controlling the lifetime of searching/indexing code (without being
> > effected by the restart of the IIS processes automatically when some
> memory
> > limit is exceeded (for ex.) )
> >
> > * Ability to access some system resources that can be restricted by IIS
> >
> > etc.
> >
> > make me think a separete search service is a better idea.But at last, it
> is
> > a design decision of you.
> >
> > (Think, A WebApp+Solr in Java world)
> >
> >
> >
> >
> >
> > DIGY
> >
> >
> >
> > > Changes to make Lucene.NET compatible with ASP.NET <http://asp.net/>
> Medium Trust Level, in hosting environments (like GoDaddy...)
> >
> > >
> >
> -----------------------------------------------------------------------------------------------------------------
> >
> > >
> >
> > > Key: LUCENENET-169
> >
> > > URL:
> https://issues.apache.org/jira/browse/LUCENENET-169
> >
> > > Project: Lucene.Net
> >
> > > Issue Type: Improvement
> >
> > > Environment: ASP.NET <http://asp.net/>
> >
> > > Reporter: Corey Trager
> >
> > > Attachments: FSDirectory.patch
> >
> > >
> >
> > >
> >
> > > Microsoft has a configuration file for shared hosting for what they
> call
> > "Medium Trust". There are a couple places in FSDirectory.cs that
> violate
> > the restrictions of Medium Trust, but I coded workarounds, shown below.
> >
> > > #1)
> >
> > > // Corey Trager, Oct 2008: Commented call to GetTempPath to workaround
> > permission restrictions at shared host.
> >
> > > // LOCK_DIR isn't used anyway.
> >
> > > public static readonly System.String LOCK_DIR = null; //
> > SupportClass.AppSettings.Get("Lucene.Net.lockDir",
> > System.IO.Path.GetTempPath());
> >
> > > #2)
> >
> > > /// <summary>Returns an array of strings, one for each
> > Lucene index file in the directory. </summary>
> >
> > > public override System.String[] List()
> >
> > > {
> >
> > > /* Changes by Corey Trager, Oct 2008, to workaround permission
> > restrictions at shared host */
> >
> > > System.IO.DirectoryInfo dir = new
> > System.IO.DirectoryInfo(directory.FullName);
> >
> > > System.IO.FileInfo[] files = dir.GetFiles();
> >
> > > string[] list = new string[files.Length];
> >
> > > for (int i = 0; i < files.Length; i++)
> >
> > > {
> >
> > > list[i] = files[i].Name;
> >
> > > }
> >
> > > return list;
> >
> > > /* end of changes */
> >
> > > // System.String[] files =
> > SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName,
> > IndexFileNameFilter.GetFilter());
> >
> > > // for (int i = 0; i < files.Length; i++)
> >
> > > // {
> >
> > > // System.IO.FileInfo fi = new
> > System.IO.FileInfo(files[i]);
> >
> > > // files[i] = fi.Name;
> >
> > > // }
> >
> > > // return files;
> >
> > > }
> >
> >
> >
> > --
> >
> > This message is automatically generated by JIRA.
> >
> > -
> >
> > You can reply to this email to add a comment to the issue online.
> >
> >
>
Re: Luke-0.9.x cannot open index files
Posted by Floyd Wu <fl...@gmail.com>.
Hi Digy,
Thanks for your help.
But if chinese field name is the problem, will it be "fix" in Lucene.Net or
how can I avoid this problem.
Chinese field name is by design and probably not avoidable.
Floyd
2009/4/25 Digy <di...@gmail.com>
> I think, I found the bug. Here is the dump of the original index:
>
>
>
> NUMDOCS: 3
>
> MAXDOCS: 7
>
> DELETED(0): True
>
> DELETED(1): True
>
> DELETED(2): False
>
> DELETED(3): True
>
> DELETED(4): True
>
> DELETED(5): False
>
> DELETED(6): False
>
> TERM(0): _l_activationdatetime:552877632000000000
>
> TERM(1): _l_author:admin
>
> TERM(2): _l_bookmarkcount:0
>
> TERM(3): _l_clix:0
>
> TERM(4): _l_clix:1
>
> TERM(5): _l_creationdatetime:633427319866778624
>
> TERM(6): _l_creationdatetime:633427324812559872
>
> TERM(7): _l_creationdatetime:633760609388437504
>
> TERM(8): _l_deactivationdatetime:155377824000000000
>
> TERM(9): _l_deactivationdatetime:155378687999969792
>
> TERM(10): _l_document_class:1
>
> TERM(11): _l_document_class:98305
>
> TERM(12): _l_folder:163841
>
> TERM(13): _l_folder:163843
>
> TERM(14): _l_hidden:aaa
>
> TERM(15): _l_last_modified_datetime:633427319866778624
>
> TERM(16): _l_last_modified_datetime:633427324812559872
>
> TERM(17): _l_last_modified_datetime:633760609388437504
>
> TERM(18): _l_meta:abc
>
> TERM(19): _l_meta:abc.ppt
>
> TERM(20): _l_meta:ddx
>
> TERM(21): _l_meta:doc
>
> TERM(22): _l_meta:xyz
>
> TERM(23): _l_meta:名
>
> TERM(24): _l_meta:問
>
> TERM(25): _l_meta:有
>
> TERM(26): _l_meta:檔
>
> TERM(27): _l_meta:測
>
> TERM(28): _l_meta:看
>
> TERM(29): _l_meta:試
>
> TERM(30): _l_meta:還
>
> TERM(31): _l_meta:題
>
> TERM(32): _l_parentdocument:196609
>
> TERM(33): _l_parentdocument:327681
>
> TERM(34): _l_parentdocument:557057
>
> TERM(35): _l_ratingavg:0
>
> TERM(36): _l_ratingmedian:0
>
> TERM(37): _l_ratingstdev:0
>
> TERM(38): _l_ratingsum:0
>
> TERM(39): _l_read_permission:admin
>
> TERM(40): _l_rootdocument:196609
>
> TERM(41): _l_rootdocument:327681
>
> TERM(42): _l_rootdocument:557057
>
> TERM(43): _l_state:0
>
> TERM(44): _l_state:2
>
> TERM(45): _l_summary:2123456789
>
> TERM(46): _l_summary:abc
>
> TERM(47): _l_summary:abc.ppt
>
> TERM(48): _l_summary:ddx
>
> TERM(49): _l_summary:doc
>
> TERM(50): _l_summary:xyz
>
> TERM(51): _l_summary:有
>
> TERM(52): _l_summary:還
>
> TERM(53): _l_title:123
>
> TERM(54): _l_title:class
>
> TERM(55): _l_title:default
>
> TERM(56): _l_title:document
>
> TERM(57): _l_title:名
>
> TERM(58): _l_title:問
>
> TERM(59): _l_title:檔
>
> TERM(60): _l_title:測
>
> TERM(61): _l_title:看
>
> TERM(62): _l_title:試
>
> TERM(63): _l_title:題
>
> TERM(64): _l_unique_key:196609
>
> TERM(65): _l_unique_key:327681
>
> TERM(66): _l_unique_key:557057
>
> TERM(67): _l_version:1
>
> TERM(68): 作者:123
>
> TERM(69): 摘要:2123456789
>
> TERM(70): 摘要:abc
>
> TERM(71): 摘要:abc.ppt
>
> TERM(72): 摘要:ddx
>
> TERM(73): 摘要:doc
>
> TERM(74): 摘要:xyz
>
> TERM(75): 摘要:有
>
> TERM(76): 摘要:還
>
> TERM(77): 標題:123
>
> TERM(78): 標題:class
>
> TERM(79): 標題:default
>
> TERM(80): 標題:document
>
> TERM(81): 標題:名
>
> TERM(82): 標題:問
>
> TERM(83): 標題:檔
>
> TERM(84): 標題:測
>
> TERM(85): 標題:看
>
> TERM(86): 標題:試
>
> TERM(87): 標題:題
>
> TERM(88): 關鍵詞:123
>
>
>
>
>
>
>
> And here is a sample code: read docs from original index and then write to
> an new one.
>
>
>
> void CreateNewIndex(string OrgIndex)
>
> {
>
> IndexReader reader = IndexReader.Open(OrgIndex);
>
> IndexWriter writer = new IndexWriter("Floyd", new
> Lucene.Net.Analysis.WhitespaceAnalyzer(),true);
>
>
>
> for (int i = 0; i < reader.MaxDoc(); i++)
>
> {
>
> if (reader.IsDeleted(i) == true) continue;
>
>
>
> Lucene.Net.Documents.Document orgDoc = reader.Document(i);
>
> System.Collections.IList fields = orgDoc.GetFields();
>
>
>
> Lucene.Net.Documents.Document newDoc = new Document();
>
> foreach (Lucene.Net.Documents.Field field in fields)
>
> {
>
> Lucene.Net.Documents.Field newField = new Field(
>
> System.Convert.ToBase64String(
> System.Text.Encoding.UTF8.GetBytes(field.Name())), //ç
>
> //field.Name(), //ç
>
> field.StringValue(),
>
> field.IsStored() ?
> Lucene.Net.Documents.Field.Store.YES : Lucene.Net.Documents.Field.Store.NO<http://lucene.net.documents.field.store.no/>
> ,
>
> field.IsTokenized() ?
> Lucene.Net.Documents.Field.Index.TOKENIZED :
> Lucene.Net.Documents.Field.Index.UN_TOKENIZED);
>
>
>
> newDoc.Add(newField);
>
> }
>
> writer.AddDocument(newDoc);
>
> }
>
>
>
> writer.Close();
>
> reader.Close();
>
> }
>
>
>
>
>
> If some field names are chinese, then Luke returns “read past EOF”. But if
> those field names are replaced with non-chinese names, then it works.
>
>
>
> DIGY
>
>
>
>
>
>
>
>
>
>
>
> -----Original Message-----
> From: Granroth, Neal V. [mailto:neal.granroth@thermofisher.com]
> Sent: Friday, April 24, 2009 8:53 PM
> To: lucene-net-dev@incubator.apache.org
> Subject: Luke-0.9.x cannot open index files
>
>
>
>
>
> Digy,
>
>
>
> Some additional information from the discussion on the lucene-net-user list
> with Floyd Wu.
>
>
>
>
>
> I ran some further tests using Java Lucene 2.3.2 and JDK 1.5.
>
>
>
> The Java equivalents of the two small test applications I use to inspect an
> index and compact it, function identically to the .NET versions (that were
> built with VS2005 and Lucene.NET 2.3.1).
>
>
>
> That Luke cannot open the index appears to be a problem within Luke.
>
> Even if Floyd's index contains some odd entries, Java Lucene 2.3.2 does not
> flag the index as corrupt; and both the Java and .NET versions report the
> same index content before and after the optimize operation.
>
>
>
>
>
> -- Neal
>
>
>
> **************************************************************
>
> Neal Granroth
>
> Software Engineer, Molecular Spectroscopy
>
> Thermo Fisher Scientific
>
> 5225 Verona Road, Madison, WI 53711
>
>
>
> neal.granroth@thermofisher.com
>
> Tel: 608-276-5645
>
> Fax: 608-276-6328
>
>
>
> www.thermofisher.com
>
>
>
> WORLDWIDE CONFIDENTIALITY NOTE: Dissemination, distribution or copying of
> this e-mail or the information herein by anyone other than the intended
> recipient, or an employee or agent of a system responsible for delivering
> the message to the intended recipient, is prohibited. If you are not the
> intended recipient, please inform the sender and delete all copies.
>
>
>
> -----Original Message-----
>
> From: Digy (JIRA) [mailto:jira@apache.org]
>
> Sent: Wednesday, April 08, 2009 6:28 PM
>
> To: lucene-net-dev@incubator.apache.org
>
> Subject: [jira] Commented: (LUCENENET-169) Changes to make Lucene.NET
> compatible with ASP.NET <http://asp.net/> Medium Trust Level, in hosting
> environments (like GoDaddy...)
>
>
>
>
>
> [
> https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12697335#action_12697335]
>
>
>
> Digy commented on LUCENENET-169:
>
> --------------------------------
>
>
>
> Although you can overcome all of them somehow;
>
>
>
> * controlling the the lifetime of IndexWriter/IndexReader in a naturally
> manner,
>
> * reopening the IndexReader only when needed using (for ex)
> FileSystemWatcher,
>
> * providing a separation between data & bussiness layer,
>
> * providing other apps an interface that may want to write its own user
> interface,
>
> * accessing a single search service from different web apps/from load
> balanced web servers
>
> * controlling the lifetime of searching/indexing code (without being
> effected by the restart of the IIS processes automatically when some memory
> limit is exceeded (for ex.) )
>
> * Ability to access some system resources that can be restricted by IIS
>
> etc.
>
> make me think a separete search service is a better idea.But at last, it is
> a design decision of you.
>
> (Think, A WebApp+Solr in Java world)
>
>
>
>
>
> DIGY
>
>
>
> > Changes to make Lucene.NET compatible with ASP.NET <http://asp.net/> Medium Trust Level, in hosting environments (like GoDaddy...)
>
> >
> -----------------------------------------------------------------------------------------------------------------
>
> >
>
> > Key: LUCENENET-169
>
> > URL: https://issues.apache.org/jira/browse/LUCENENET-169
>
> > Project: Lucene.Net
>
> > Issue Type: Improvement
>
> > Environment: ASP.NET <http://asp.net/>
>
> > Reporter: Corey Trager
>
> > Attachments: FSDirectory.patch
>
> >
>
> >
>
> > Microsoft has a configuration file for shared hosting for what they call
> "Medium Trust". There are a couple places in FSDirectory.cs that violate
> the restrictions of Medium Trust, but I coded workarounds, shown below.
>
> > #1)
>
> > // Corey Trager, Oct 2008: Commented call to GetTempPath to workaround
> permission restrictions at shared host.
>
> > // LOCK_DIR isn't used anyway.
>
> > public static readonly System.String LOCK_DIR = null; //
> SupportClass.AppSettings.Get("Lucene.Net.lockDir",
> System.IO.Path.GetTempPath());
>
> > #2)
>
> > /// <summary>Returns an array of strings, one for each
> Lucene index file in the directory. </summary>
>
> > public override System.String[] List()
>
> > {
>
> > /* Changes by Corey Trager, Oct 2008, to workaround permission
> restrictions at shared host */
>
> > System.IO.DirectoryInfo dir = new
> System.IO.DirectoryInfo(directory.FullName);
>
> > System.IO.FileInfo[] files = dir.GetFiles();
>
> > string[] list = new string[files.Length];
>
> > for (int i = 0; i < files.Length; i++)
>
> > {
>
> > list[i] = files[i].Name;
>
> > }
>
> > return list;
>
> > /* end of changes */
>
> > // System.String[] files =
> SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName,
> IndexFileNameFilter.GetFilter());
>
> > // for (int i = 0; i < files.Length; i++)
>
> > // {
>
> > // System.IO.FileInfo fi = new
> System.IO.FileInfo(files[i]);
>
> > // files[i] = fi.Name;
>
> > // }
>
> > // return files;
>
> > }
>
>
>
> --
>
> This message is automatically generated by JIRA.
>
> -
>
> You can reply to this email to add a comment to the issue online.
>
>
RE: Luke-0.9.x cannot open index files
Posted by Digy <di...@gmail.com>.
I think, I found the bug. Here is the dump of the original index:
NUMDOCS: 3
MAXDOCS: 7
DELETED(0): True
DELETED(1): True
DELETED(2): False
DELETED(3): True
DELETED(4): True
DELETED(5): False
DELETED(6): False
TERM(0): _l_activationdatetime:552877632000000000
TERM(1): _l_author:admin
TERM(2): _l_bookmarkcount:0
TERM(3): _l_clix:0
TERM(4): _l_clix:1
TERM(5): _l_creationdatetime:633427319866778624
TERM(6): _l_creationdatetime:633427324812559872
TERM(7): _l_creationdatetime:633760609388437504
TERM(8): _l_deactivationdatetime:155377824000000000
TERM(9): _l_deactivationdatetime:155378687999969792
TERM(10): _l_document_class:1
TERM(11): _l_document_class:98305
TERM(12): _l_folder:163841
TERM(13): _l_folder:163843
TERM(14): _l_hidden:aaa
TERM(15): _l_last_modified_datetime:633427319866778624
TERM(16): _l_last_modified_datetime:633427324812559872
TERM(17): _l_last_modified_datetime:633760609388437504
TERM(18): _l_meta:abc
TERM(19): _l_meta:abc.ppt
TERM(20): _l_meta:ddx
TERM(21): _l_meta:doc
TERM(22): _l_meta:xyz
TERM(23): _l_meta:名
TERM(24): _l_meta:問
TERM(25): _l_meta:有
TERM(26): _l_meta:檔
TERM(27): _l_meta:測
TERM(28): _l_meta:看
TERM(29): _l_meta:試
TERM(30): _l_meta:還
TERM(31): _l_meta:題
TERM(32): _l_parentdocument:196609
TERM(33): _l_parentdocument:327681
TERM(34): _l_parentdocument:557057
TERM(35): _l_ratingavg:0
TERM(36): _l_ratingmedian:0
TERM(37): _l_ratingstdev:0
TERM(38): _l_ratingsum:0
TERM(39): _l_read_permission:admin
TERM(40): _l_rootdocument:196609
TERM(41): _l_rootdocument:327681
TERM(42): _l_rootdocument:557057
TERM(43): _l_state:0
TERM(44): _l_state:2
TERM(45): _l_summary:2123456789
TERM(46): _l_summary:abc
TERM(47): _l_summary:abc.ppt
TERM(48): _l_summary:ddx
TERM(49): _l_summary:doc
TERM(50): _l_summary:xyz
TERM(51): _l_summary:有
TERM(52): _l_summary:還
TERM(53): _l_title:123
TERM(54): _l_title:class
TERM(55): _l_title:default
TERM(56): _l_title:document
TERM(57): _l_title:名
TERM(58): _l_title:問
TERM(59): _l_title:檔
TERM(60): _l_title:測
TERM(61): _l_title:看
TERM(62): _l_title:試
TERM(63): _l_title:題
TERM(64): _l_unique_key:196609
TERM(65): _l_unique_key:327681
TERM(66): _l_unique_key:557057
TERM(67): _l_version:1
TERM(68): 作者:123
TERM(69): 摘要:2123456789
TERM(70): 摘要:abc
TERM(71): 摘要:abc.ppt
TERM(72): 摘要:ddx
TERM(73): 摘要:doc
TERM(74): 摘要:xyz
TERM(75): 摘要:有
TERM(76): 摘要:還
TERM(77): 標題:123
TERM(78): 標題:class
TERM(79): 標題:default
TERM(80): 標題:document
TERM(81): 標題:名
TERM(82): 標題:問
TERM(83): 標題:檔
TERM(84): 標題:測
TERM(85): 標題:看
TERM(86): 標題:試
TERM(87): 標題:題
TERM(88): 關鍵詞:123
And here is a sample code: read docs from original index and then write to an new one.
void CreateNewIndex(string OrgIndex)
{
IndexReader reader = IndexReader.Open(OrgIndex);
IndexWriter writer = new IndexWriter("Floyd", new Lucene.Net.Analysis.WhitespaceAnalyzer(),true);
for (int i = 0; i < reader.MaxDoc(); i++)
{
if (reader.IsDeleted(i) == true) continue;
Lucene.Net.Documents.Document orgDoc = reader.Document(i);
System.Collections.IList fields = orgDoc.GetFields();
Lucene.Net.Documents.Document newDoc = new Document();
foreach (Lucene.Net.Documents.Field field in fields)
{
Lucene.Net.Documents.Field newField = new Field(
System.Convert.ToBase64String( System.Text.Encoding.UTF8.GetBytes(field.Name())), //ç
//field.Name(), //ç
field.StringValue(),
field.IsStored() ? Lucene.Net.Documents.Field.Store.YES : Lucene.Net.Documents.Field.Store.NO,
field.IsTokenized() ? Lucene.Net.Documents.Field.Index.TOKENIZED : Lucene.Net.Documents.Field.Index.UN_TOKENIZED);
newDoc.Add(newField);
}
writer.AddDocument(newDoc);
}
writer.Close();
reader.Close();
}
If some field names are chinese, then Luke returns “read past EOF”. But if those field names are replaced with non-chinese names, then it works.
DIGY
-----Original Message-----
From: Granroth, Neal V. [mailto:neal.granroth@thermofisher.com]
Sent: Friday, April 24, 2009 8:53 PM
To: lucene-net-dev@incubator.apache.org
Subject: Luke-0.9.x cannot open index files
Digy,
Some additional information from the discussion on the lucene-net-user list with Floyd Wu.
I ran some further tests using Java Lucene 2.3.2 and JDK 1.5.
The Java equivalents of the two small test applications I use to inspect an index and compact it, function identically to the .NET versions (that were built with VS2005 and Lucene.NET 2.3.1).
That Luke cannot open the index appears to be a problem within Luke.
Even if Floyd's index contains some odd entries, Java Lucene 2.3.2 does not flag the index as corrupt; and both the Java and .NET versions report the same index content before and after the optimize operation.
-- Neal
**************************************************************
Neal Granroth
Software Engineer, Molecular Spectroscopy
Thermo Fisher Scientific
5225 Verona Road, Madison, WI 53711
neal.granroth@thermofisher.com
Tel: 608-276-5645
Fax: 608-276-6328
www.thermofisher.com
WORLDWIDE CONFIDENTIALITY NOTE: Dissemination, distribution or copying of this e-mail or the information herein by anyone other than the intended recipient, or an employee or agent of a system responsible for delivering the message to the intended recipient, is prohibited. If you are not the intended recipient, please inform the sender and delete all copies.
-----Original Message-----
From: Digy (JIRA) [mailto:jira@apache.org]
Sent: Wednesday, April 08, 2009 6:28 PM
To: lucene-net-dev@incubator.apache.org
Subject: [jira] Commented: (LUCENENET-169) Changes to make Lucene.NET compatible with ASP.NET Medium Trust Level, in hosting environments (like GoDaddy...)
[ https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12697335#action_12697335 ]
Digy commented on LUCENENET-169:
--------------------------------
Although you can overcome all of them somehow;
* controlling the the lifetime of IndexWriter/IndexReader in a naturally manner,
* reopening the IndexReader only when needed using (for ex) FileSystemWatcher,
* providing a separation between data & bussiness layer,
* providing other apps an interface that may want to write its own user interface,
* accessing a single search service from different web apps/from load balanced web servers
* controlling the lifetime of searching/indexing code (without being effected by the restart of the IIS processes automatically when some memory limit is exceeded (for ex.) )
* Ability to access some system resources that can be restricted by IIS
etc.
make me think a separete search service is a better idea.But at last, it is a design decision of you.
(Think, A WebApp+Solr in Java world)
DIGY
> Changes to make Lucene.NET compatible with ASP.NET Medium Trust Level, in hosting environments (like GoDaddy...)
> -----------------------------------------------------------------------------------------------------------------
>
> Key: LUCENENET-169
> URL: https://issues.apache.org/jira/browse/LUCENENET-169
> Project: Lucene.Net
> Issue Type: Improvement
> Environment: ASP.NET
> Reporter: Corey Trager
> Attachments: FSDirectory.patch
>
>
> Microsoft has a configuration file for shared hosting for what they call "Medium Trust". There are a couple places in FSDirectory.cs that violate the restrictions of Medium Trust, but I coded workarounds, shown below.
> #1)
> // Corey Trager, Oct 2008: Commented call to GetTempPath to workaround permission restrictions at shared host.
> // LOCK_DIR isn't used anyway.
> public static readonly System.String LOCK_DIR = null; // SupportClass.AppSettings.Get("Lucene.Net.lockDir", System.IO.Path.GetTempPath());
> #2)
> /// <summary>Returns an array of strings, one for each Lucene index file in the directory. </summary>
> public override System.String[] List()
> {
> /* Changes by Corey Trager, Oct 2008, to workaround permission restrictions at shared host */
> System.IO.DirectoryInfo dir = new System.IO.DirectoryInfo(directory.FullName);
> System.IO.FileInfo[] files = dir.GetFiles();
> string[] list = new string[files.Length];
> for (int i = 0; i < files.Length; i++)
> {
> list[i] = files[i].Name;
> }
> return list;
> /* end of changes */
> // System.String[] files = SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName, IndexFileNameFilter.GetFilter());
> // for (int i = 0; i < files.Length; i++)
> // {
> // System.IO.FileInfo fi = new System.IO.FileInfo(files[i]);
> // files[i] = fi.Name;
> // }
> // return files;
> }
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
RE: Luke-0.9.x cannot open index files
Posted by Digy <di...@gmail.com>.
I think, I found the bug. Here is the dump of the original index:
NUMDOCS: 3
MAXDOCS: 7
DELETED(0): True
DELETED(1): True
DELETED(2): False
DELETED(3): True
DELETED(4): True
DELETED(5): False
DELETED(6): False
TERM(0): _l_activationdatetime:552877632000000000
TERM(1): _l_author:admin
TERM(2): _l_bookmarkcount:0
TERM(3): _l_clix:0
TERM(4): _l_clix:1
TERM(5): _l_creationdatetime:633427319866778624
TERM(6): _l_creationdatetime:633427324812559872
TERM(7): _l_creationdatetime:633760609388437504
TERM(8): _l_deactivationdatetime:155377824000000000
TERM(9): _l_deactivationdatetime:155378687999969792
TERM(10): _l_document_class:1
TERM(11): _l_document_class:98305
TERM(12): _l_folder:163841
TERM(13): _l_folder:163843
TERM(14): _l_hidden:aaa
TERM(15): _l_last_modified_datetime:633427319866778624
TERM(16): _l_last_modified_datetime:633427324812559872
TERM(17): _l_last_modified_datetime:633760609388437504
TERM(18): _l_meta:abc
TERM(19): _l_meta:abc.ppt
TERM(20): _l_meta:ddx
TERM(21): _l_meta:doc
TERM(22): _l_meta:xyz
TERM(23): _l_meta:名
TERM(24): _l_meta:問
TERM(25): _l_meta:有
TERM(26): _l_meta:檔
TERM(27): _l_meta:測
TERM(28): _l_meta:看
TERM(29): _l_meta:試
TERM(30): _l_meta:還
TERM(31): _l_meta:題
TERM(32): _l_parentdocument:196609
TERM(33): _l_parentdocument:327681
TERM(34): _l_parentdocument:557057
TERM(35): _l_ratingavg:0
TERM(36): _l_ratingmedian:0
TERM(37): _l_ratingstdev:0
TERM(38): _l_ratingsum:0
TERM(39): _l_read_permission:admin
TERM(40): _l_rootdocument:196609
TERM(41): _l_rootdocument:327681
TERM(42): _l_rootdocument:557057
TERM(43): _l_state:0
TERM(44): _l_state:2
TERM(45): _l_summary:2123456789
TERM(46): _l_summary:abc
TERM(47): _l_summary:abc.ppt
TERM(48): _l_summary:ddx
TERM(49): _l_summary:doc
TERM(50): _l_summary:xyz
TERM(51): _l_summary:有
TERM(52): _l_summary:還
TERM(53): _l_title:123
TERM(54): _l_title:class
TERM(55): _l_title:default
TERM(56): _l_title:document
TERM(57): _l_title:名
TERM(58): _l_title:問
TERM(59): _l_title:檔
TERM(60): _l_title:測
TERM(61): _l_title:看
TERM(62): _l_title:試
TERM(63): _l_title:題
TERM(64): _l_unique_key:196609
TERM(65): _l_unique_key:327681
TERM(66): _l_unique_key:557057
TERM(67): _l_version:1
TERM(68): 作者:123
TERM(69): 摘要:2123456789
TERM(70): 摘要:abc
TERM(71): 摘要:abc.ppt
TERM(72): 摘要:ddx
TERM(73): 摘要:doc
TERM(74): 摘要:xyz
TERM(75): 摘要:有
TERM(76): 摘要:還
TERM(77): 標題:123
TERM(78): 標題:class
TERM(79): 標題:default
TERM(80): 標題:document
TERM(81): 標題:名
TERM(82): 標題:問
TERM(83): 標題:檔
TERM(84): 標題:測
TERM(85): 標題:看
TERM(86): 標題:試
TERM(87): 標題:題
TERM(88): 關鍵詞:123
And here is a sample code: read docs from original index and then write to an new one.
void CreateNewIndex(string OrgIndex)
{
IndexReader reader = IndexReader.Open(OrgIndex);
IndexWriter writer = new IndexWriter("Floyd", new Lucene.Net.Analysis.WhitespaceAnalyzer(),true);
for (int i = 0; i < reader.MaxDoc(); i++)
{
if (reader.IsDeleted(i) == true) continue;
Lucene.Net.Documents.Document orgDoc = reader.Document(i);
System.Collections.IList fields = orgDoc.GetFields();
Lucene.Net.Documents.Document newDoc = new Document();
foreach (Lucene.Net.Documents.Field field in fields)
{
Lucene.Net.Documents.Field newField = new Field(
System.Convert.ToBase64String( System.Text.Encoding.UTF8.GetBytes(field.Name())), //ç
//field.Name(), //ç
field.StringValue(),
field.IsStored() ? Lucene.Net.Documents.Field.Store.YES : Lucene.Net.Documents.Field.Store.NO,
field.IsTokenized() ? Lucene.Net.Documents.Field.Index.TOKENIZED : Lucene.Net.Documents.Field.Index.UN_TOKENIZED);
newDoc.Add(newField);
}
writer.AddDocument(newDoc);
}
writer.Close();
reader.Close();
}
If some field names are chinese, then Luke returns “read past EOF”. But if those field names are replaced with non-chinese names, then it works.
DIGY
-----Original Message-----
From: Granroth, Neal V. [mailto:neal.granroth@thermofisher.com]
Sent: Friday, April 24, 2009 8:53 PM
To: lucene-net-dev@incubator.apache.org
Subject: Luke-0.9.x cannot open index files
Digy,
Some additional information from the discussion on the lucene-net-user list with Floyd Wu.
I ran some further tests using Java Lucene 2.3.2 and JDK 1.5.
The Java equivalents of the two small test applications I use to inspect an index and compact it, function identically to the .NET versions (that were built with VS2005 and Lucene.NET 2.3.1).
That Luke cannot open the index appears to be a problem within Luke.
Even if Floyd's index contains some odd entries, Java Lucene 2.3.2 does not flag the index as corrupt; and both the Java and .NET versions report the same index content before and after the optimize operation.
-- Neal
**************************************************************
Neal Granroth
Software Engineer, Molecular Spectroscopy
Thermo Fisher Scientific
5225 Verona Road, Madison, WI 53711
neal.granroth@thermofisher.com
Tel: 608-276-5645
Fax: 608-276-6328
www.thermofisher.com
WORLDWIDE CONFIDENTIALITY NOTE: Dissemination, distribution or copying of this e-mail or the information herein by anyone other than the intended recipient, or an employee or agent of a system responsible for delivering the message to the intended recipient, is prohibited. If you are not the intended recipient, please inform the sender and delete all copies.
-----Original Message-----
From: Digy (JIRA) [mailto:jira@apache.org]
Sent: Wednesday, April 08, 2009 6:28 PM
To: lucene-net-dev@incubator.apache.org
Subject: [jira] Commented: (LUCENENET-169) Changes to make Lucene.NET compatible with ASP.NET Medium Trust Level, in hosting environments (like GoDaddy...)
[ https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12697335#action_12697335 ]
Digy commented on LUCENENET-169:
--------------------------------
Although you can overcome all of them somehow;
* controlling the the lifetime of IndexWriter/IndexReader in a naturally manner,
* reopening the IndexReader only when needed using (for ex) FileSystemWatcher,
* providing a separation between data & bussiness layer,
* providing other apps an interface that may want to write its own user interface,
* accessing a single search service from different web apps/from load balanced web servers
* controlling the lifetime of searching/indexing code (without being effected by the restart of the IIS processes automatically when some memory limit is exceeded (for ex.) )
* Ability to access some system resources that can be restricted by IIS
etc.
make me think a separete search service is a better idea.But at last, it is a design decision of you.
(Think, A WebApp+Solr in Java world)
DIGY
> Changes to make Lucene.NET compatible with ASP.NET Medium Trust Level, in hosting environments (like GoDaddy...)
> -----------------------------------------------------------------------------------------------------------------
>
> Key: LUCENENET-169
> URL: https://issues.apache.org/jira/browse/LUCENENET-169
> Project: Lucene.Net
> Issue Type: Improvement
> Environment: ASP.NET
> Reporter: Corey Trager
> Attachments: FSDirectory.patch
>
>
> Microsoft has a configuration file for shared hosting for what they call "Medium Trust". There are a couple places in FSDirectory.cs that violate the restrictions of Medium Trust, but I coded workarounds, shown below.
> #1)
> // Corey Trager, Oct 2008: Commented call to GetTempPath to workaround permission restrictions at shared host.
> // LOCK_DIR isn't used anyway.
> public static readonly System.String LOCK_DIR = null; // SupportClass.AppSettings.Get("Lucene.Net.lockDir", System.IO.Path.GetTempPath());
> #2)
> /// <summary>Returns an array of strings, one for each Lucene index file in the directory. </summary>
> public override System.String[] List()
> {
> /* Changes by Corey Trager, Oct 2008, to workaround permission restrictions at shared host */
> System.IO.DirectoryInfo dir = new System.IO.DirectoryInfo(directory.FullName);
> System.IO.FileInfo[] files = dir.GetFiles();
> string[] list = new string[files.Length];
> for (int i = 0; i < files.Length; i++)
> {
> list[i] = files[i].Name;
> }
> return list;
> /* end of changes */
> // System.String[] files = SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName, IndexFileNameFilter.GetFilter());
> // for (int i = 0; i < files.Length; i++)
> // {
> // System.IO.FileInfo fi = new System.IO.FileInfo(files[i]);
> // files[i] = fi.Name;
> // }
> // return files;
> }
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
Luke-0.9.x cannot open index files
Posted by "Granroth, Neal V." <ne...@thermofisher.com>.
Digy,
Some additional information from the discussion on the lucene-net-user list with Floyd Wu.
I ran some further tests using Java Lucene 2.3.2 and JDK 1.5.
The Java equivalents of the two small test applications I use to inspect an index and compact it, function identically to the .NET versions (that were built with VS2005 and Lucene.NET 2.3.1).
That Luke cannot open the index appears to be a problem within Luke.
Even if Floyd's index contains some odd entries, Java Lucene 2.3.2 does not flag the index as corrupt; and both the Java and .NET versions report the same index content before and after the optimize operation.
-- Neal
**************************************************************
Neal Granroth
Software Engineer, Molecular Spectroscopy
Thermo Fisher Scientific
5225 Verona Road, Madison, WI 53711
neal.granroth@thermofisher.com
Tel: 608-276-5645
Fax: 608-276-6328
www.thermofisher.com
WORLDWIDE CONFIDENTIALITY NOTE: Dissemination, distribution or copying of this e-mail or the information herein by anyone other than the intended recipient, or an employee or agent of a system responsible for delivering the message to the intended recipient, is prohibited. If you are not the intended recipient, please inform the sender and delete all copies.
-----Original Message-----
From: Digy (JIRA) [mailto:jira@apache.org]
Sent: Wednesday, April 08, 2009 6:28 PM
To: lucene-net-dev@incubator.apache.org
Subject: [jira] Commented: (LUCENENET-169) Changes to make Lucene.NET compatible with ASP.NET Medium Trust Level, in hosting environments (like GoDaddy...)
[ https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12697335#action_12697335 ]
Digy commented on LUCENENET-169:
--------------------------------
Although you can overcome all of them somehow;
* controlling the the lifetime of IndexWriter/IndexReader in a naturally manner,
* reopening the IndexReader only when needed using (for ex) FileSystemWatcher,
* providing a separation between data & bussiness layer,
* providing other apps an interface that may want to write its own user interface,
* accessing a single search service from different web apps/from load balanced web servers
* controlling the lifetime of searching/indexing code (without being effected by the restart of the IIS processes automatically when some memory limit is exceeded (for ex.) )
* Ability to access some system resources that can be restricted by IIS
etc.
make me think a separete search service is a better idea.But at last, it is a design decision of you.
(Think, A WebApp+Solr in Java world)
DIGY
> Changes to make Lucene.NET compatible with ASP.NET Medium Trust Level, in hosting environments (like GoDaddy...)
> -----------------------------------------------------------------------------------------------------------------
>
> Key: LUCENENET-169
> URL: https://issues.apache.org/jira/browse/LUCENENET-169
> Project: Lucene.Net
> Issue Type: Improvement
> Environment: ASP.NET
> Reporter: Corey Trager
> Attachments: FSDirectory.patch
>
>
> Microsoft has a configuration file for shared hosting for what they call "Medium Trust". There are a couple places in FSDirectory.cs that violate the restrictions of Medium Trust, but I coded workarounds, shown below.
> #1)
> // Corey Trager, Oct 2008: Commented call to GetTempPath to workaround permission restrictions at shared host.
> // LOCK_DIR isn't used anyway.
> public static readonly System.String LOCK_DIR = null; // SupportClass.AppSettings.Get("Lucene.Net.lockDir", System.IO.Path.GetTempPath());
> #2)
> /// <summary>Returns an array of strings, one for each Lucene index file in the directory. </summary>
> public override System.String[] List()
> {
> /* Changes by Corey Trager, Oct 2008, to workaround permission restrictions at shared host */
> System.IO.DirectoryInfo dir = new System.IO.DirectoryInfo(directory.FullName);
> System.IO.FileInfo[] files = dir.GetFiles();
> string[] list = new string[files.Length];
> for (int i = 0; i < files.Length; i++)
> {
> list[i] = files[i].Name;
> }
> return list;
> /* end of changes */
> // System.String[] files = SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName, IndexFileNameFilter.GetFilter());
> // for (int i = 0; i < files.Length; i++)
> // {
> // System.IO.FileInfo fi = new System.IO.FileInfo(files[i]);
> // files[i] = fi.Name;
> // }
> // return files;
> }
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (LUCENENET-169) Changes to make Lucene.NET
compatible with ASP.NET Medium Trust Level, in hosting environments (like
GoDaddy...)
Posted by "Luis Fco. Ramirez Daza Glez. (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12719145#action_12719145 ]
Luis Fco. Ramirez Daza Glez. commented on LUCENENET-169:
--------------------------------------------------------
Hi all
Definitly there are a lot of applications that can benefit of using Lucene in MEDIUM TRUST.
We already have an application that we want to use in shared hosting enviroments. Planning a new one. And I'm also thinking of adding Lucene to DotNetNuke, that also will require MEDIUM TRUST.
*COREY*: Are you planning to work on the patch for the GetLuceneIndexFiles?
> Changes to make Lucene.NET compatible with ASP.NET Medium Trust Level, in hosting environments (like GoDaddy...)
> -----------------------------------------------------------------------------------------------------------------
>
> Key: LUCENENET-169
> URL: https://issues.apache.org/jira/browse/LUCENENET-169
> Project: Lucene.Net
> Issue Type: Improvement
> Environment: ASP.NET
> Reporter: Corey Trager
> Attachments: FSDirectory.patch
>
>
> Microsoft has a configuration file for shared hosting for what they call "Medium Trust". There are a couple places in FSDirectory.cs that violate the restrictions of Medium Trust, but I coded workarounds, shown below.
> #1)
> // Corey Trager, Oct 2008: Commented call to GetTempPath to workaround permission restrictions at shared host.
> // LOCK_DIR isn't used anyway.
> public static readonly System.String LOCK_DIR = null; // SupportClass.AppSettings.Get("Lucene.Net.lockDir", System.IO.Path.GetTempPath());
> #2)
> /// <summary>Returns an array of strings, one for each Lucene index file in the directory. </summary>
> public override System.String[] List()
> {
> /* Changes by Corey Trager, Oct 2008, to workaround permission restrictions at shared host */
> System.IO.DirectoryInfo dir = new System.IO.DirectoryInfo(directory.FullName);
> System.IO.FileInfo[] files = dir.GetFiles();
> string[] list = new string[files.Length];
> for (int i = 0; i < files.Length; i++)
> {
> list[i] = files[i].Name;
> }
> return list;
> /* end of changes */
> // System.String[] files = SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName, IndexFileNameFilter.GetFilter());
> // for (int i = 0; i < files.Length; i++)
> // {
> // System.IO.FileInfo fi = new System.IO.FileInfo(files[i]);
> // files[i] = fi.Name;
> // }
> // return files;
> }
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (LUCENENET-169) Changes to make Lucene.NET
compatible with ASP.NET Medium Trust Level, in hosting environments (like
GoDaddy...)
Posted by "Corey Trager (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12719189#action_12719189 ]
Corey Trager commented on LUCENENET-169:
----------------------------------------
I found what was causing the "Required permissions cannot be acquired" with Medium Trust.
You have to go to project settings, Build, and uncheck "Allow unsafe code".
Pretty simple to say, but took me about three hours of trial and error to narrow down which svn revision the problem got introduced into, and then to narrow down the difference between that revision and the prior.
Some links that I found after that fact:
http://www.codeplex.com/AntiXSS/Thread/View.aspx?ThreadId=44517
http://social.msdn.microsoft.com/Forums/en-US/clr/thread/77376b96-5512-4c38-8c07-a527e577ec3a
> Changes to make Lucene.NET compatible with ASP.NET Medium Trust Level, in hosting environments (like GoDaddy...)
> -----------------------------------------------------------------------------------------------------------------
>
> Key: LUCENENET-169
> URL: https://issues.apache.org/jira/browse/LUCENENET-169
> Project: Lucene.Net
> Issue Type: Improvement
> Environment: ASP.NET
> Reporter: Corey Trager
> Attachments: FSDirectory.patch
>
>
> Microsoft has a configuration file for shared hosting for what they call "Medium Trust". There are a couple places in FSDirectory.cs that violate the restrictions of Medium Trust, but I coded workarounds, shown below.
> #1)
> // Corey Trager, Oct 2008: Commented call to GetTempPath to workaround permission restrictions at shared host.
> // LOCK_DIR isn't used anyway.
> public static readonly System.String LOCK_DIR = null; // SupportClass.AppSettings.Get("Lucene.Net.lockDir", System.IO.Path.GetTempPath());
> #2)
> /// <summary>Returns an array of strings, one for each Lucene index file in the directory. </summary>
> public override System.String[] List()
> {
> /* Changes by Corey Trager, Oct 2008, to workaround permission restrictions at shared host */
> System.IO.DirectoryInfo dir = new System.IO.DirectoryInfo(directory.FullName);
> System.IO.FileInfo[] files = dir.GetFiles();
> string[] list = new string[files.Length];
> for (int i = 0; i < files.Length; i++)
> {
> list[i] = files[i].Name;
> }
> return list;
> /* end of changes */
> // System.String[] files = SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName, IndexFileNameFilter.GetFilter());
> // for (int i = 0; i < files.Length; i++)
> // {
> // System.IO.FileInfo fi = new System.IO.FileInfo(files[i]);
> // files[i] = fi.Name;
> // }
> // return files;
> }
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (LUCENENET-169) Changes to make Lucene.NET
compatible with ASP.NET Medium Trust Level, in hosting environments (like
GoDaddy...)
Posted by "Digy (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12697335#action_12697335 ]
Digy commented on LUCENENET-169:
--------------------------------
Although you can overcome all of them somehow;
* controlling the the lifetime of IndexWriter/IndexReader in a naturally manner,
* reopening the IndexReader only when needed using (for ex) FileSystemWatcher,
* providing a separation between data & bussiness layer,
* providing other apps an interface that may want to write its own user interface,
* accessing a single search service from different web apps/from load balanced web servers
* controlling the lifetime of searching/indexing code (without being effected by the restart of the IIS processes automatically when some memory limit is exceeded (for ex.) )
* Ability to access some system resources that can be restricted by IIS
etc.
make me think a separete search service is a better idea.But at last, it is a design decision of you.
(Think, A WebApp+Solr in Java world)
DIGY
> Changes to make Lucene.NET compatible with ASP.NET Medium Trust Level, in hosting environments (like GoDaddy...)
> -----------------------------------------------------------------------------------------------------------------
>
> Key: LUCENENET-169
> URL: https://issues.apache.org/jira/browse/LUCENENET-169
> Project: Lucene.Net
> Issue Type: Improvement
> Environment: ASP.NET
> Reporter: Corey Trager
> Attachments: FSDirectory.patch
>
>
> Microsoft has a configuration file for shared hosting for what they call "Medium Trust". There are a couple places in FSDirectory.cs that violate the restrictions of Medium Trust, but I coded workarounds, shown below.
> #1)
> // Corey Trager, Oct 2008: Commented call to GetTempPath to workaround permission restrictions at shared host.
> // LOCK_DIR isn't used anyway.
> public static readonly System.String LOCK_DIR = null; // SupportClass.AppSettings.Get("Lucene.Net.lockDir", System.IO.Path.GetTempPath());
> #2)
> /// <summary>Returns an array of strings, one for each Lucene index file in the directory. </summary>
> public override System.String[] List()
> {
> /* Changes by Corey Trager, Oct 2008, to workaround permission restrictions at shared host */
> System.IO.DirectoryInfo dir = new System.IO.DirectoryInfo(directory.FullName);
> System.IO.FileInfo[] files = dir.GetFiles();
> string[] list = new string[files.Length];
> for (int i = 0; i < files.Length; i++)
> {
> list[i] = files[i].Name;
> }
> return list;
> /* end of changes */
> // System.String[] files = SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName, IndexFileNameFilter.GetFilter());
> // for (int i = 0; i < files.Length; i++)
> // {
> // System.IO.FileInfo fi = new System.IO.FileInfo(files[i]);
> // files[i] = fi.Name;
> // }
> // return files;
> }
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Updated: (LUCENENET-169) Changes to make Lucene.NET
compatible with ASP.NET Medium Trust Level, in hosting environments (like
GoDaddy...)
Posted by "Digy (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Digy updated LUCENENET-169:
---------------------------
Attachment: FSDirectory.patch
The redundant for-loop in FSDirectory#List method is carried over from Lucene.Net 2.0 where "System.IO.Directory.GetFileSystemEntries" ( _which incorrectly returned *all* files in index dir with *full* name_) was used instead of "SupportClass.FileSupport.GetLuceneIndexFiles".
All NUnite tests pass. If no objections, I will commit the last patch and close this issue.
DIGY
> Changes to make Lucene.NET compatible with ASP.NET Medium Trust Level, in hosting environments (like GoDaddy...)
> -----------------------------------------------------------------------------------------------------------------
>
> Key: LUCENENET-169
> URL: https://issues.apache.org/jira/browse/LUCENENET-169
> Project: Lucene.Net
> Issue Type: Improvement
> Environment: ASP.NET
> Reporter: Corey Trager
> Attachments: FSDirectory-mediumtrust.patch, FSDirectory.patch, FSDirectory.patch
>
>
> Microsoft has a configuration file for shared hosting for what they call "Medium Trust". There are a couple places in FSDirectory.cs that violate the restrictions of Medium Trust, but I coded workarounds, shown below.
> #1)
> // Corey Trager, Oct 2008: Commented call to GetTempPath to workaround permission restrictions at shared host.
> // LOCK_DIR isn't used anyway.
> public static readonly System.String LOCK_DIR = null; // SupportClass.AppSettings.Get("Lucene.Net.lockDir", System.IO.Path.GetTempPath());
> #2)
> /// <summary>Returns an array of strings, one for each Lucene index file in the directory. </summary>
> public override System.String[] List()
> {
> /* Changes by Corey Trager, Oct 2008, to workaround permission restrictions at shared host */
> System.IO.DirectoryInfo dir = new System.IO.DirectoryInfo(directory.FullName);
> System.IO.FileInfo[] files = dir.GetFiles();
> string[] list = new string[files.Length];
> for (int i = 0; i < files.Length; i++)
> {
> list[i] = files[i].Name;
> }
> return list;
> /* end of changes */
> // System.String[] files = SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName, IndexFileNameFilter.GetFilter());
> // for (int i = 0; i < files.Length; i++)
> // {
> // System.IO.FileInfo fi = new System.IO.FileInfo(files[i]);
> // files[i] = fi.Name;
> // }
> // return files;
> }
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Updated: (LUCENENET-169) Changes to make Lucene.NET
compatible with ASP.NET Medium Trust Level, in hosting environments (like
GoDaddy...)
Posted by "Martijn Boland (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Martijn Boland updated LUCENENET-169:
-------------------------------------
Attachment: FSDirectory-mediumtrust.patch
No need to change GetLuceneIndexFiles. The problem was creating a new FileInfo object with a relative path, which is not allowed under medium trust.
Attached is a patch that fixes the issue. Tested it and it now works under medium trust.
> Changes to make Lucene.NET compatible with ASP.NET Medium Trust Level, in hosting environments (like GoDaddy...)
> -----------------------------------------------------------------------------------------------------------------
>
> Key: LUCENENET-169
> URL: https://issues.apache.org/jira/browse/LUCENENET-169
> Project: Lucene.Net
> Issue Type: Improvement
> Environment: ASP.NET
> Reporter: Corey Trager
> Attachments: FSDirectory-mediumtrust.patch, FSDirectory.patch
>
>
> Microsoft has a configuration file for shared hosting for what they call "Medium Trust". There are a couple places in FSDirectory.cs that violate the restrictions of Medium Trust, but I coded workarounds, shown below.
> #1)
> // Corey Trager, Oct 2008: Commented call to GetTempPath to workaround permission restrictions at shared host.
> // LOCK_DIR isn't used anyway.
> public static readonly System.String LOCK_DIR = null; // SupportClass.AppSettings.Get("Lucene.Net.lockDir", System.IO.Path.GetTempPath());
> #2)
> /// <summary>Returns an array of strings, one for each Lucene index file in the directory. </summary>
> public override System.String[] List()
> {
> /* Changes by Corey Trager, Oct 2008, to workaround permission restrictions at shared host */
> System.IO.DirectoryInfo dir = new System.IO.DirectoryInfo(directory.FullName);
> System.IO.FileInfo[] files = dir.GetFiles();
> string[] list = new string[files.Length];
> for (int i = 0; i < files.Length; i++)
> {
> list[i] = files[i].Name;
> }
> return list;
> /* end of changes */
> // System.String[] files = SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName, IndexFileNameFilter.GetFilter());
> // for (int i = 0; i < files.Length; i++)
> // {
> // System.IO.FileInfo fi = new System.IO.FileInfo(files[i]);
> // files[i] = fi.Name;
> // }
> // return files;
> }
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (LUCENENET-169) Changes to make Lucene.NET
compatible with ASP.NET Medium Trust Level, in hosting environments (like
GoDaddy...)
Posted by "Corey Trager (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12697200#action_12697200 ]
Corey Trager commented on LUCENENET-169:
----------------------------------------
Regarding Medium Trust, Microsoft's out-of-the-box default Medium Trust config file is what it is. I read that some shared hosting companies tweak it, others don't. Using Lucene.NET in the real world just goes smoother if Lucene.NET doesn't conflict with the Microsoft defaults.
Regarding:
* Is it correct to use Lucene.Net in an ASP.Net app. or should there be a search service which can be accessed by IIS or directly from client apps?
* Isn't it easier to control the lifetime of IndexReader and/or IndexWriter in an application(Console,Windows, Service) other than in IIS.
I don't know of any shared hosting company that would let you run your own Windows service, so building Lucene.NET into the ASP.NET code itself is the only realistic practical option. And, for my app, BugTracker.NET, it's working great for me and the hundreds/thousands of people who are also running it. Nobody has reported any issues with the architecture.
I've documented how I integrated Lucene.NET into my ASP.NET application here:
http://ifdefined.com/blog/post/2009/02/Full-Text-Search-in-ASPNET-using-LuceneNET.aspx
> Changes to make Lucene.NET compatible with ASP.NET Medium Trust Level, in hosting environments (like GoDaddy...)
> -----------------------------------------------------------------------------------------------------------------
>
> Key: LUCENENET-169
> URL: https://issues.apache.org/jira/browse/LUCENENET-169
> Project: Lucene.Net
> Issue Type: Improvement
> Environment: ASP.NET
> Reporter: Corey Trager
> Attachments: FSDirectory.patch
>
>
> Microsoft has a configuration file for shared hosting for what they call "Medium Trust". There are a couple places in FSDirectory.cs that violate the restrictions of Medium Trust, but I coded workarounds, shown below.
> #1)
> // Corey Trager, Oct 2008: Commented call to GetTempPath to workaround permission restrictions at shared host.
> // LOCK_DIR isn't used anyway.
> public static readonly System.String LOCK_DIR = null; // SupportClass.AppSettings.Get("Lucene.Net.lockDir", System.IO.Path.GetTempPath());
> #2)
> /// <summary>Returns an array of strings, one for each Lucene index file in the directory. </summary>
> public override System.String[] List()
> {
> /* Changes by Corey Trager, Oct 2008, to workaround permission restrictions at shared host */
> System.IO.DirectoryInfo dir = new System.IO.DirectoryInfo(directory.FullName);
> System.IO.FileInfo[] files = dir.GetFiles();
> string[] list = new string[files.Length];
> for (int i = 0; i < files.Length; i++)
> {
> list[i] = files[i].Name;
> }
> return list;
> /* end of changes */
> // System.String[] files = SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName, IndexFileNameFilter.GetFilter());
> // for (int i = 0; i < files.Length; i++)
> // {
> // System.IO.FileInfo fi = new System.IO.FileInfo(files[i]);
> // files[i] = fi.Name;
> // }
> // return files;
> }
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (LUCENENET-169) Changes to make Lucene.NET
compatible with ASP.NET Medium Trust Level, in hosting environments (like
GoDaddy...)
Posted by "Digy (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12697169#action_12697169 ]
Digy commented on LUCENENET-169:
--------------------------------
Orginal code
{code}
public override System.String[] List()
{
System.String[] files = SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName, IndexFileNameFilter.GetFilter());
for (int i = 0; i < files.Length; i++)
{
System.IO.FileInfo fi = new System.IO.FileInfo(files[i]);
files[i] = fi.Name;
}
return files;
}
{code}
returns only the files belonging to Lucene.Net index
but the proposed one
{code}
public override System.String[] List()
{
/* Changes by Corey Trager, Oct 2008, to workaround permission restrictions at shared host */
System.IO.DirectoryInfo dir = new System.IO.DirectoryInfo(directory.FullName);
System.IO.FileInfo[] files = dir.GetFiles();
string[] list = new string[files.Length];
for (int i = 0; i < files.Length; i++)
{
list[i] = files[i].Name;
}
return list;
}
{code}
returns all the files in the index directory.
A better solution would be to change the "SupportClass.FileSupport.GetLuceneIndexFiles" so that it supports Medium Trust level.
DIGY
> Changes to make Lucene.NET compatible with ASP.NET Medium Trust Level, in hosting environments (like GoDaddy...)
> -----------------------------------------------------------------------------------------------------------------
>
> Key: LUCENENET-169
> URL: https://issues.apache.org/jira/browse/LUCENENET-169
> Project: Lucene.Net
> Issue Type: Improvement
> Environment: ASP.NET
> Reporter: Corey Trager
> Attachments: FSDirectory.patch
>
>
> Microsoft has a configuration file for shared hosting for what they call "Medium Trust". There are a couple places in FSDirectory.cs that violate the restrictions of Medium Trust, but I coded workarounds, shown below.
> #1)
> // Corey Trager, Oct 2008: Commented call to GetTempPath to workaround permission restrictions at shared host.
> // LOCK_DIR isn't used anyway.
> public static readonly System.String LOCK_DIR = null; // SupportClass.AppSettings.Get("Lucene.Net.lockDir", System.IO.Path.GetTempPath());
> #2)
> /// <summary>Returns an array of strings, one for each Lucene index file in the directory. </summary>
> public override System.String[] List()
> {
> /* Changes by Corey Trager, Oct 2008, to workaround permission restrictions at shared host */
> System.IO.DirectoryInfo dir = new System.IO.DirectoryInfo(directory.FullName);
> System.IO.FileInfo[] files = dir.GetFiles();
> string[] list = new string[files.Length];
> for (int i = 0; i < files.Length; i++)
> {
> list[i] = files[i].Name;
> }
> return list;
> /* end of changes */
> // System.String[] files = SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName, IndexFileNameFilter.GetFilter());
> // for (int i = 0; i < files.Length; i++)
> // {
> // System.IO.FileInfo fi = new System.IO.FileInfo(files[i]);
> // files[i] = fi.Name;
> // }
> // return files;
> }
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (LUCENENET-169) Changes to make Lucene.NET
compatible with ASP.NET Medium Trust Level, in hosting environments (like
GoDaddy...)
Posted by "Corey Trager (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12723627#action_12723627 ]
Corey Trager commented on LUCENENET-169:
----------------------------------------
Digy - Please uncheck "Allow unsafe code".
> Changes to make Lucene.NET compatible with ASP.NET Medium Trust Level, in hosting environments (like GoDaddy...)
> -----------------------------------------------------------------------------------------------------------------
>
> Key: LUCENENET-169
> URL: https://issues.apache.org/jira/browse/LUCENENET-169
> Project: Lucene.Net
> Issue Type: Improvement
> Environment: ASP.NET
> Reporter: Corey Trager
> Attachments: FSDirectory-mediumtrust.patch, FSDirectory.patch, FSDirectory.patch
>
>
> Microsoft has a configuration file for shared hosting for what they call "Medium Trust". There are a couple places in FSDirectory.cs that violate the restrictions of Medium Trust, but I coded workarounds, shown below.
> #1)
> // Corey Trager, Oct 2008: Commented call to GetTempPath to workaround permission restrictions at shared host.
> // LOCK_DIR isn't used anyway.
> public static readonly System.String LOCK_DIR = null; // SupportClass.AppSettings.Get("Lucene.Net.lockDir", System.IO.Path.GetTempPath());
> #2)
> /// <summary>Returns an array of strings, one for each Lucene index file in the directory. </summary>
> public override System.String[] List()
> {
> /* Changes by Corey Trager, Oct 2008, to workaround permission restrictions at shared host */
> System.IO.DirectoryInfo dir = new System.IO.DirectoryInfo(directory.FullName);
> System.IO.FileInfo[] files = dir.GetFiles();
> string[] list = new string[files.Length];
> for (int i = 0; i < files.Length; i++)
> {
> list[i] = files[i].Name;
> }
> return list;
> /* end of changes */
> // System.String[] files = SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName, IndexFileNameFilter.GetFilter());
> // for (int i = 0; i < files.Length; i++)
> // {
> // System.IO.FileInfo fi = new System.IO.FileInfo(files[i]);
> // files[i] = fi.Name;
> // }
> // return files;
> }
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (LUCENENET-169) Changes to make Lucene.NET
compatible with ASP.NET Medium Trust Level, in hosting environments (like
GoDaddy...)
Posted by "Digy (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12697181#action_12697181 ]
Digy commented on LUCENENET-169:
--------------------------------
After reading that doc; http://msdn.microsoft.com/en-us/library/ms998341.aspx
* Is this really a problem of Lucene.Net?
* Is it correct to use Lucene.Net in an ASP.Net app. or should there be a search service which can be accessed by IIS or directly from client apps?
* Isn't it easier to control the lifetime of IndexReader and/or IndexWriter in an application(Console,Windows, Service) other than in IIS.
DIGY
> Changes to make Lucene.NET compatible with ASP.NET Medium Trust Level, in hosting environments (like GoDaddy...)
> -----------------------------------------------------------------------------------------------------------------
>
> Key: LUCENENET-169
> URL: https://issues.apache.org/jira/browse/LUCENENET-169
> Project: Lucene.Net
> Issue Type: Improvement
> Environment: ASP.NET
> Reporter: Corey Trager
> Attachments: FSDirectory.patch
>
>
> Microsoft has a configuration file for shared hosting for what they call "Medium Trust". There are a couple places in FSDirectory.cs that violate the restrictions of Medium Trust, but I coded workarounds, shown below.
> #1)
> // Corey Trager, Oct 2008: Commented call to GetTempPath to workaround permission restrictions at shared host.
> // LOCK_DIR isn't used anyway.
> public static readonly System.String LOCK_DIR = null; // SupportClass.AppSettings.Get("Lucene.Net.lockDir", System.IO.Path.GetTempPath());
> #2)
> /// <summary>Returns an array of strings, one for each Lucene index file in the directory. </summary>
> public override System.String[] List()
> {
> /* Changes by Corey Trager, Oct 2008, to workaround permission restrictions at shared host */
> System.IO.DirectoryInfo dir = new System.IO.DirectoryInfo(directory.FullName);
> System.IO.FileInfo[] files = dir.GetFiles();
> string[] list = new string[files.Length];
> for (int i = 0; i < files.Length; i++)
> {
> list[i] = files[i].Name;
> }
> return list;
> /* end of changes */
> // System.String[] files = SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName, IndexFileNameFilter.GetFilter());
> // for (int i = 0; i < files.Length; i++)
> // {
> // System.IO.FileInfo fi = new System.IO.FileInfo(files[i]);
> // files[i] = fi.Name;
> // }
> // return files;
> }
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Closed: (LUCENENET-169) Changes to make Lucene.NET
compatible with ASP.NET Medium Trust Level, in hosting environments (like
GoDaddy...)
Posted by "Digy (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Digy closed LUCENENET-169.
--------------------------
Resolution: Fixed
"Allow unsafe code" unchecked.
Patch applied.
DIGY
> Changes to make Lucene.NET compatible with ASP.NET Medium Trust Level, in hosting environments (like GoDaddy...)
> -----------------------------------------------------------------------------------------------------------------
>
> Key: LUCENENET-169
> URL: https://issues.apache.org/jira/browse/LUCENENET-169
> Project: Lucene.Net
> Issue Type: Improvement
> Environment: ASP.NET
> Reporter: Corey Trager
> Attachments: FSDirectory-mediumtrust.patch, FSDirectory.patch, FSDirectory.patch
>
>
> Microsoft has a configuration file for shared hosting for what they call "Medium Trust". There are a couple places in FSDirectory.cs that violate the restrictions of Medium Trust, but I coded workarounds, shown below.
> #1)
> // Corey Trager, Oct 2008: Commented call to GetTempPath to workaround permission restrictions at shared host.
> // LOCK_DIR isn't used anyway.
> public static readonly System.String LOCK_DIR = null; // SupportClass.AppSettings.Get("Lucene.Net.lockDir", System.IO.Path.GetTempPath());
> #2)
> /// <summary>Returns an array of strings, one for each Lucene index file in the directory. </summary>
> public override System.String[] List()
> {
> /* Changes by Corey Trager, Oct 2008, to workaround permission restrictions at shared host */
> System.IO.DirectoryInfo dir = new System.IO.DirectoryInfo(directory.FullName);
> System.IO.FileInfo[] files = dir.GetFiles();
> string[] list = new string[files.Length];
> for (int i = 0; i < files.Length; i++)
> {
> list[i] = files[i].Name;
> }
> return list;
> /* end of changes */
> // System.String[] files = SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName, IndexFileNameFilter.GetFilter());
> // for (int i = 0; i < files.Length; i++)
> // {
> // System.IO.FileInfo fi = new System.IO.FileInfo(files[i]);
> // files[i] = fi.Name;
> // }
> // return files;
> }
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Updated: (LUCENENET-169) Changes to make Lucene.NET
compatible with ASP.NET Medium Trust Level, in hosting environments (like
GoDaddy...)
Posted by "Digy (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Digy updated LUCENENET-169:
---------------------------
Attachment: FSDirectory.patch
Since LOCK_DIR is depreciated with 2.1 and not used anymore in 2.3.x, I plan to commit the "FSDirectory.patch" soon.
DIGY
> Changes to make Lucene.NET compatible with ASP.NET Medium Trust Level, in hosting environments (like GoDaddy...)
> -----------------------------------------------------------------------------------------------------------------
>
> Key: LUCENENET-169
> URL: https://issues.apache.org/jira/browse/LUCENENET-169
> Project: Lucene.Net
> Issue Type: Improvement
> Environment: ASP.NET
> Reporter: Corey Trager
> Attachments: FSDirectory.patch
>
>
> Microsoft has a configuration file for shared hosting for what they call "Medium Trust". There are a couple places in FSDirectory.cs that violate the restrictions of Medium Trust, but I coded workarounds, shown below.
> #1)
> // Corey Trager, Oct 2008: Commented call to GetTempPath to workaround permission restrictions at shared host.
> // LOCK_DIR isn't used anyway.
> public static readonly System.String LOCK_DIR = null; // SupportClass.AppSettings.Get("Lucene.Net.lockDir", System.IO.Path.GetTempPath());
> #2)
> /// <summary>Returns an array of strings, one for each Lucene index file in the directory. </summary>
> public override System.String[] List()
> {
> /* Changes by Corey Trager, Oct 2008, to workaround permission restrictions at shared host */
> System.IO.DirectoryInfo dir = new System.IO.DirectoryInfo(directory.FullName);
> System.IO.FileInfo[] files = dir.GetFiles();
> string[] list = new string[files.Length];
> for (int i = 0; i < files.Length; i++)
> {
> list[i] = files[i].Name;
> }
> return list;
> /* end of changes */
> // System.String[] files = SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName, IndexFileNameFilter.GetFilter());
> // for (int i = 0; i < files.Length; i++)
> // {
> // System.IO.FileInfo fi = new System.IO.FileInfo(files[i]);
> // files[i] = fi.Name;
> // }
> // return files;
> }
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (LUCENENET-169) Changes to make Lucene.NET
compatible with ASP.NET Medium Trust Level, in hosting environments (like
GoDaddy...)
Posted by "Digy (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12697223#action_12697223 ]
Digy commented on LUCENENET-169:
--------------------------------
Alltough I still think that implementing search services in an Web Application is not a good idea, I can understand that you don't want to change your architecture.
So can you send a patch that doesn't change the logic of GetLuceneIndexFiles and compatible with "Medium Trust Level"?
(PS: I don't remember anybody who is blaming BugTracker.NET, it is more related with how to use the Lucene.Net)
DIGY
> Changes to make Lucene.NET compatible with ASP.NET Medium Trust Level, in hosting environments (like GoDaddy...)
> -----------------------------------------------------------------------------------------------------------------
>
> Key: LUCENENET-169
> URL: https://issues.apache.org/jira/browse/LUCENENET-169
> Project: Lucene.Net
> Issue Type: Improvement
> Environment: ASP.NET
> Reporter: Corey Trager
> Attachments: FSDirectory.patch
>
>
> Microsoft has a configuration file for shared hosting for what they call "Medium Trust". There are a couple places in FSDirectory.cs that violate the restrictions of Medium Trust, but I coded workarounds, shown below.
> #1)
> // Corey Trager, Oct 2008: Commented call to GetTempPath to workaround permission restrictions at shared host.
> // LOCK_DIR isn't used anyway.
> public static readonly System.String LOCK_DIR = null; // SupportClass.AppSettings.Get("Lucene.Net.lockDir", System.IO.Path.GetTempPath());
> #2)
> /// <summary>Returns an array of strings, one for each Lucene index file in the directory. </summary>
> public override System.String[] List()
> {
> /* Changes by Corey Trager, Oct 2008, to workaround permission restrictions at shared host */
> System.IO.DirectoryInfo dir = new System.IO.DirectoryInfo(directory.FullName);
> System.IO.FileInfo[] files = dir.GetFiles();
> string[] list = new string[files.Length];
> for (int i = 0; i < files.Length; i++)
> {
> list[i] = files[i].Name;
> }
> return list;
> /* end of changes */
> // System.String[] files = SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName, IndexFileNameFilter.GetFilter());
> // for (int i = 0; i < files.Length; i++)
> // {
> // System.IO.FileInfo fi = new System.IO.FileInfo(files[i]);
> // files[i] = fi.Name;
> // }
> // return files;
> }
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (LUCENENET-169) Changes to make Lucene.NET
compatible with ASP.NET Medium Trust Level, in hosting environments (like
GoDaddy...)
Posted by "Corey Trager (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12719178#action_12719178 ]
Corey Trager commented on LUCENENET-169:
----------------------------------------
@Luis - Here's what I did today. I fetched the latest code from svn, built, and tried to run. I got an error message "Required permissions cannot be acquired". The callstack does not tell me what the offending code or even permission is. I applied the changes already documented here (I only needed #2), but that didn't help.
I then fetched the Lucene.NET cod with revision 703747 and I was able to run under Medium Trust on my machine without alterning the code at all. It was way back in October when I had the problems on GoDaddy and I'm not sure if my problems were ever with the default Medium Trust configuration like my machine. Maybe GoDaddy's customized their Medium Trust. configuration? I don't want to experiment with my site on GoDaddy because I don't want the disruption.
It would take me a lot of trial and error to figure out what the changes are since svn revision 703747 that conflict with my own default Medium Trust, and then to experiment with workarounds..... I think I'm just going to have to stick wih 703747.
We are the only ones who would like to see Lucene.NET compatible with Medium Trust:
http://social.msdn.microsoft.com/Forums/en-US/windowsazure/thread/d0ec059b-f136-488b-ab74-c2f4c95c659c
http://www.mojoportal.com/mediumtrust.aspx
http://www.klopfenstein.net/lorenz.aspx/lucene-net-and-nhibernate-search-on-medium-trust
http://dev.communityserver.com/forums/p/478315/544018.aspx
> Changes to make Lucene.NET compatible with ASP.NET Medium Trust Level, in hosting environments (like GoDaddy...)
> -----------------------------------------------------------------------------------------------------------------
>
> Key: LUCENENET-169
> URL: https://issues.apache.org/jira/browse/LUCENENET-169
> Project: Lucene.Net
> Issue Type: Improvement
> Environment: ASP.NET
> Reporter: Corey Trager
> Attachments: FSDirectory.patch
>
>
> Microsoft has a configuration file for shared hosting for what they call "Medium Trust". There are a couple places in FSDirectory.cs that violate the restrictions of Medium Trust, but I coded workarounds, shown below.
> #1)
> // Corey Trager, Oct 2008: Commented call to GetTempPath to workaround permission restrictions at shared host.
> // LOCK_DIR isn't used anyway.
> public static readonly System.String LOCK_DIR = null; // SupportClass.AppSettings.Get("Lucene.Net.lockDir", System.IO.Path.GetTempPath());
> #2)
> /// <summary>Returns an array of strings, one for each Lucene index file in the directory. </summary>
> public override System.String[] List()
> {
> /* Changes by Corey Trager, Oct 2008, to workaround permission restrictions at shared host */
> System.IO.DirectoryInfo dir = new System.IO.DirectoryInfo(directory.FullName);
> System.IO.FileInfo[] files = dir.GetFiles();
> string[] list = new string[files.Length];
> for (int i = 0; i < files.Length; i++)
> {
> list[i] = files[i].Name;
> }
> return list;
> /* end of changes */
> // System.String[] files = SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName, IndexFileNameFilter.GetFilter());
> // for (int i = 0; i < files.Length; i++)
> // {
> // System.IO.FileInfo fi = new System.IO.FileInfo(files[i]);
> // files[i] = fi.Name;
> // }
> // return files;
> }
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (LUCENENET-169) Changes to make Lucene.NET
compatible with ASP.NET Medium Trust Level, in hosting environments (like
GoDaddy...)
Posted by "Luis Fco. Ramirez Daza Glez. (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12719210#action_12719210 ]
Luis Fco. Ramirez Daza Glez. commented on LUCENENET-169:
--------------------------------------------------------
Thank you Corey for your help and for share this with us.
I'll do as you explained to make Lucene work in MEDIUM TRUST and post my results.
> Changes to make Lucene.NET compatible with ASP.NET Medium Trust Level, in hosting environments (like GoDaddy...)
> -----------------------------------------------------------------------------------------------------------------
>
> Key: LUCENENET-169
> URL: https://issues.apache.org/jira/browse/LUCENENET-169
> Project: Lucene.Net
> Issue Type: Improvement
> Environment: ASP.NET
> Reporter: Corey Trager
> Attachments: FSDirectory.patch
>
>
> Microsoft has a configuration file for shared hosting for what they call "Medium Trust". There are a couple places in FSDirectory.cs that violate the restrictions of Medium Trust, but I coded workarounds, shown below.
> #1)
> // Corey Trager, Oct 2008: Commented call to GetTempPath to workaround permission restrictions at shared host.
> // LOCK_DIR isn't used anyway.
> public static readonly System.String LOCK_DIR = null; // SupportClass.AppSettings.Get("Lucene.Net.lockDir", System.IO.Path.GetTempPath());
> #2)
> /// <summary>Returns an array of strings, one for each Lucene index file in the directory. </summary>
> public override System.String[] List()
> {
> /* Changes by Corey Trager, Oct 2008, to workaround permission restrictions at shared host */
> System.IO.DirectoryInfo dir = new System.IO.DirectoryInfo(directory.FullName);
> System.IO.FileInfo[] files = dir.GetFiles();
> string[] list = new string[files.Length];
> for (int i = 0; i < files.Length; i++)
> {
> list[i] = files[i].Name;
> }
> return list;
> /* end of changes */
> // System.String[] files = SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName, IndexFileNameFilter.GetFilter());
> // for (int i = 0; i < files.Length; i++)
> // {
> // System.IO.FileInfo fi = new System.IO.FileInfo(files[i]);
> // files[i] = fi.Name;
> // }
> // return files;
> }
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (LUCENENET-169) Changes to make Lucene.NET
compatible with ASP.NET Medium Trust Level, in hosting environments (like
GoDaddy...)
Posted by "Corey Trager (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/LUCENENET-169?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12697248#action_12697248 ]
Corey Trager commented on LUCENENET-169:
----------------------------------------
I'll see if I can change the code. I didn't even pay attention to the filter argument. Oops.
....Again, regarding the architecture, I'm not understanding. Before I integrated it into my ASP.NET, I didn't know if it would work well or not, but it has worked well, so, isn't the proof in the pudding? Do you have specific concerns? If you prefer to contact me directly, at ctrager@yahoo.com, that's ok, or if you prefer to drop the topic, that's ok too....
> Changes to make Lucene.NET compatible with ASP.NET Medium Trust Level, in hosting environments (like GoDaddy...)
> -----------------------------------------------------------------------------------------------------------------
>
> Key: LUCENENET-169
> URL: https://issues.apache.org/jira/browse/LUCENENET-169
> Project: Lucene.Net
> Issue Type: Improvement
> Environment: ASP.NET
> Reporter: Corey Trager
> Attachments: FSDirectory.patch
>
>
> Microsoft has a configuration file for shared hosting for what they call "Medium Trust". There are a couple places in FSDirectory.cs that violate the restrictions of Medium Trust, but I coded workarounds, shown below.
> #1)
> // Corey Trager, Oct 2008: Commented call to GetTempPath to workaround permission restrictions at shared host.
> // LOCK_DIR isn't used anyway.
> public static readonly System.String LOCK_DIR = null; // SupportClass.AppSettings.Get("Lucene.Net.lockDir", System.IO.Path.GetTempPath());
> #2)
> /// <summary>Returns an array of strings, one for each Lucene index file in the directory. </summary>
> public override System.String[] List()
> {
> /* Changes by Corey Trager, Oct 2008, to workaround permission restrictions at shared host */
> System.IO.DirectoryInfo dir = new System.IO.DirectoryInfo(directory.FullName);
> System.IO.FileInfo[] files = dir.GetFiles();
> string[] list = new string[files.Length];
> for (int i = 0; i < files.Length; i++)
> {
> list[i] = files[i].Name;
> }
> return list;
> /* end of changes */
> // System.String[] files = SupportClass.FileSupport.GetLuceneIndexFiles(directory.FullName, IndexFileNameFilter.GetFilter());
> // for (int i = 0; i < files.Length; i++)
> // {
> // System.IO.FileInfo fi = new System.IO.FileInfo(files[i]);
> // files[i] = fi.Name;
> // }
> // return files;
> }
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.