mirror of
https://github.com/yacy/yacy_search_server.git
synced 2024-09-21 00:00:13 +02:00
5c3afb3202
this shall be used to store a fragment of the index on another physical device, to split IO load and enhance access speed. The index is splitted in such a way that the LURLs are stored to the secondary location, and the RWIs to the primary location. This is especially useful for environments where symbolic links are not possible and may cause IO access even if there is no write access to the device which hosts the symbolic link. git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@3519 6c8d7289-2bf4-0310-a012-ef5d649a1542
271 lines
9.9 KiB
HTML
271 lines
9.9 KiB
HTML
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
|
|
<html xmlns="http://www.w3.org/1999/xhtml">
|
|
<head>
|
|
<title>YaCy '#[clientname]#': Index Import</title>
|
|
#%env/templates/metas.template%#
|
|
<meta http-equiv="REFRESH" content="30" />
|
|
</head>
|
|
<body id="IndexImport">
|
|
#%env/templates/header.template%#
|
|
#%env/templates/submenuIndexControl.template%#
|
|
<h2>Index DB Import</h2>
|
|
<p>The local index currently consists of (at least) #[wcount]# reverse word indexes and #[ucount]# URL references.</p>
|
|
#(error)#<!-- 0 -->
|
|
::<!-- 1 -->
|
|
<p class="error">#[error_msg]#</p>
|
|
::<!-- 2 -->
|
|
<p class="error">Import Job with the same path already started.</p>
|
|
::<!-- 3 -->
|
|
<p class="error">#[error_msg]#</p>
|
|
<p class="error"><code>#[error_stackTrace]#</code></p>
|
|
#(/error)#
|
|
<form action="IndexImport_p.html" method="post" enctype="multipart/form-data">
|
|
<h3>Starting new Job</h3>
|
|
<table border="0" cellpadding="2" cellspacing="1">
|
|
<tr class="TableCellLight">
|
|
<td>Import Type:</td>
|
|
<td title="the path to the database that should be imported">
|
|
<select name="importType" size="1">
|
|
<!-- Options not availible because of missing support for Assortment DB's
|
|
<option value="plasmaDB">PLASMA DB Import</option>
|
|
<option value="assortment">Assortment File Import</option>-->
|
|
<option value="NURL">Crawling Queue Import</option>
|
|
</select>
|
|
</td>
|
|
<td title="the cache size that should be used for the import db">Cache Size</td>
|
|
<td>
|
|
<select name="cacheSize" size="1">
|
|
<option value="2097152">2 MB</option>
|
|
<option value="4194304">4 MB</option>
|
|
<option value="8388608" selected="selected">8 MB</option>
|
|
<option value="16777216">16 MB</option>
|
|
<option value="33554432">32 MB</option>
|
|
<option value="67108864">64 MB</option>
|
|
<option value="134217728">128 MB</option>
|
|
</select>
|
|
</td>
|
|
<td><a href="#usage">Usage Examples</a></td>
|
|
</tr>
|
|
<tr class="TableCellLight">
|
|
<td title="Path to the PLASMADB directory of the foreign peer">Import Path:</td>
|
|
<td colspan="3"><input name="importPlasmaPath" type="text" size="50" value="" /></td>
|
|
<td></td>
|
|
</tr>
|
|
<tr class="TableCellLight">
|
|
<td title="Path to the primary Index directory of the foreign peer">Import Path:</td>
|
|
<td colspan="3"><input name="importIndexPrimaryPath" type="text" size="50" value="" /></td>
|
|
<td></td>
|
|
</tr>
|
|
<tr class="TableCellLight">
|
|
<td title="Path to the secondary Index directory of the foreign peer">Import Path:</td>
|
|
<td colspan="3"><input name="importIndexSecondaryPath" type="text" size="50" value="" /></td>
|
|
<td><input type="submit" name="startIndexDbImport" value="Start Import" /></td>
|
|
</tr>
|
|
</table>
|
|
<p class="warning"><strong>Attention:</strong><br />Always do a backup of your source and destination database before starting to use this import function.</p>
|
|
</form>
|
|
|
|
<hr />
|
|
<h3>Currently running jobs</h3>
|
|
<table border="0" cellpadding="2" cellspacing="1">
|
|
<colgroup>
|
|
<col />
|
|
<col width="150" />
|
|
<col span="7" />
|
|
</colgroup>
|
|
<tr class="TableHeader" valign="bottom">
|
|
<td>Job Type</td>
|
|
<td>Job Name</td>
|
|
<td>Status</td>
|
|
<td>%</td>
|
|
<td>Elapsed<br />Time</td>
|
|
<td>Time<br />Left</td>
|
|
<td>Import Status</td>
|
|
<td>Abort Import</td>
|
|
<td>Pause Import</td>
|
|
</tr>
|
|
#{running.jobs}#
|
|
<form action="IndexImport_p.html" method="post" enctype="multipart/form-data">
|
|
<tr class="TableCellLight">
|
|
<td>#[type]#</td>
|
|
<td title="#[fullName]#">#[shortName]#</td>
|
|
<td style="color:#(runningStatus)#red::green::blue#(/runningStatus)#;">#(runningStatus)#Finished::Running::Paused#(/runningStatus)#</td>
|
|
<td align="right">#[percent]#</td>
|
|
<td align="right">#[elapsed]#</td>
|
|
<td align="right">#[estimated]#</td>
|
|
<td align="left"><tt>#[status]#</tt></td>
|
|
<td>
|
|
<input type="hidden" name="jobNr" value="#[job_nr]#" />
|
|
#(stopped)#::
|
|
<input type="submit" name="stopIndexDbImport" value="Abort" />
|
|
#(/stopped)#
|
|
</td>
|
|
<td>
|
|
#(paused)#
|
|
<input type="submit" name="pauseIndexDbImport" value="Pause" />
|
|
::
|
|
<input type="submit" name="continueIndexDbImport" value="Continue" />
|
|
#(/paused)#
|
|
</td>
|
|
</tr>
|
|
</form>
|
|
#{/running.jobs}#
|
|
</table>
|
|
|
|
|
|
<hr />
|
|
<form action="IndexImport_p.html" method="post" enctype="multipart/form-data">
|
|
<h3>Finished jobs</h3>
|
|
<table border="0" cellpadding="2" cellspacing="1">
|
|
<colgroup>
|
|
<col />
|
|
<col width="150" />
|
|
<col span="4" />
|
|
</colgroup>
|
|
<tr class="TableHeader" valign="bottom">
|
|
<td>Job Type</td>
|
|
<td>Path</td>
|
|
<td>Status</td>
|
|
<td>%</td>
|
|
<td>Elapsed<br />Time</td>
|
|
<td>Import Status</td>
|
|
</tr>
|
|
#{finished.jobs}#
|
|
<tr class="TableCellLight">
|
|
<td>#[type]#</td>
|
|
<td title="#[fullName]#">#[shortName]#</td>
|
|
<td><font color="#(runningStatus)#green::red::blue#(/runningStatus)#">#(runningStatus)#Finished::<b>Error:</b> #[errorMsg]#::Paused#(/runningStatus)#</font></td>
|
|
<td align="right">#[percent]#</td>
|
|
<td align="right">#[elapsed]#</td>
|
|
<td align="left"><tt>#[status]#</tt></td>
|
|
</tr>
|
|
#{/finished.jobs}#
|
|
</table>
|
|
<fieldset>
|
|
<input type="submit" name="clearFinishedJobList" value="Clear List" />
|
|
</fieldset>
|
|
</form>
|
|
<p><em>Last Refresh:</em> #[date]#</p>
|
|
<hr />
|
|
<h2 id="usage">Usage Examples:</h2>
|
|
|
|
<!--<h3>Plasma DB Import:</h3>
|
|
<p>
|
|
<strong>Example Path:</strong> <tt>E:\PLASMADB\</tt>
|
|
</p>
|
|
<p>
|
|
<strong>Requirements:</strong>
|
|
</p>
|
|
<p>
|
|
You need to have at least the following directories and files in this path:
|
|
</p>
|
|
<table border="1" cellpadding="2" cellspacing="1">
|
|
<tr class="example">
|
|
<td>Name</td>
|
|
<td>Type</td>
|
|
<td>Writeable</td>
|
|
<td>Description</td>
|
|
</tr>
|
|
<tr>
|
|
<td><tt>urlHash.db</tt></td>
|
|
<td>File</td>
|
|
<td>No</td>
|
|
<td>The LoadedURL Database containing all loaded and indexed URLs</td>
|
|
</tr>
|
|
<tr>
|
|
<td><tt>ACLUSTER</tt></td>
|
|
<td>Directory</td>
|
|
<td>Yes</td>
|
|
<td>The assortment directory containing parts of the word index.</td>
|
|
</tr>
|
|
<tr>
|
|
<td><tt>WORDS</tt></td>
|
|
<td>Directory</td>
|
|
<td>Yes</td>
|
|
<td>The words directory containing parts of the word index.</td>
|
|
</tr>
|
|
</table>
|
|
|
|
<h3>Assortment Import:</h3>
|
|
<p>
|
|
<strong>Example Path:</strong> <tt>E:\PLASMADB\ACLUSTER\indexAssortment001.db</tt>
|
|
</p>
|
|
<p>
|
|
<strong>Requirements:</strong>
|
|
</p>
|
|
<p>
|
|
You need to have at least the following directories and files in this path:
|
|
</p>
|
|
<table border="1" cellpadding="2" cellspacing="1">
|
|
<tr class="example">
|
|
<td>Name</td>
|
|
<td>Type</td>
|
|
<td>Writeable</td>
|
|
<td>Description</td>
|
|
</tr>
|
|
<tr>
|
|
<td><tt>indexAssortment001.db</tt></td>
|
|
<td>File</td>
|
|
<td>No</td>
|
|
<td>The assortment file that should be imported.<br />
|
|
<strong>Attention:</strong> The assortment file must have the postfix "[0-9]{3}\.db".
|
|
If you would like to import an assortment file from the <tt>PLASMADB\ACLUSTER\ABKP</tt>
|
|
you have to rename it first.
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
<p>
|
|
<strong>Notes:</strong>
|
|
</p>
|
|
<p>
|
|
Please note that the imported words are useless if the destination peer doesn't know
|
|
the URLs the imported words belongs to.
|
|
</p>-->
|
|
|
|
<h3>Crawling Queue Import:</h3>
|
|
<p>
|
|
<strong>Example Path:</strong> <tt>E:\PLASMADB\</tt>
|
|
</p>
|
|
<p>
|
|
<strong>Requirements:</strong>
|
|
</p>
|
|
<p>
|
|
You need to have at least the following directories and files in this path:
|
|
</p>
|
|
<table border="1" cellpadding="2" cellspacing="1">
|
|
<tr class="example">
|
|
<td>Name</td>
|
|
<td>Type</td>
|
|
<td>Writeable</td>
|
|
<td>Description</td>
|
|
</tr>
|
|
<tr>
|
|
<td><tt>crawlProfiles0.db</tt></td>
|
|
<td>File</td>
|
|
<td>No</td>
|
|
<td>Contains data about the crawljob an URL belongs to</td>
|
|
</tr>
|
|
<tr>
|
|
<td><tt>urlNotice1.db</tt></td>
|
|
<td>File</td>
|
|
<td>Yes</td>
|
|
<td>The crawling queue</td>
|
|
</tr>
|
|
<tr>
|
|
<td><tt>urlNoticeImage0.stack</tt></td>
|
|
<td rowspan="8">File</td>
|
|
<td rowspan="8">Yes</td>
|
|
<td rowspan="8">Various stack files that belong to the crawling queue</td>
|
|
</tr>
|
|
<tr><td><tt>urlNoticeImage0.stack</tt></td></tr>
|
|
<tr><td><tt>urlNoticeLimit0.stack</tt></td></tr>
|
|
<tr><td><tt>urlNoticeLocal0.stack</tt></td></tr>
|
|
<tr><td><tt>urlNoticeMovie0.stack</tt></td></tr>
|
|
<tr><td><tt>urlNoticeMusic0.stack</tt></td></tr>
|
|
<tr><td><tt>urlNoticeOverhang0.stack</tt></td></tr>
|
|
<tr><td><tt>urlNoticeRemote0.stack</tt></td></tr>
|
|
</table>
|
|
|
|
#%env/templates/footer.template%#
|
|
</body>
|
|
</html> |