mirror of
https://github.com/yacy/yacy_search_server.git
synced 2024-09-19 00:01:41 +02:00
1bab4ffe20
This can be seen as a fix for https://github.com/yacy/yacy_search_server/issues/343 however, the export was not flawed, it is just the impression that something is wrong, but the export size must be smaller than the index size because the index also containers error documents. Now an information line is presented that shows i.e.: "The local index currently contains 181,319 documents, only 106,887 exportable with status code 200 - the remaining are error documents."
104 lines
5.6 KiB
HTML
104 lines
5.6 KiB
HTML
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "DTD/xhtml1-transitional.dtd">
|
|
<!-- This page is only XHTML 1.0 Transitional because target is being used in a links -->
|
|
<html xmlns="http://www.w3.org/1999/xhtml">
|
|
#(reload)#::<meta http-equiv="REFRESH" content="5; url=/IndexExport_p.html">#(/reload)#
|
|
<head>
|
|
<title>YaCy '#[clientname]#': URL Database Administration</title>
|
|
#%env/templates/metas.template%#
|
|
</head>
|
|
<body id="IndexControl">
|
|
#%env/templates/header.template%#
|
|
#%env/templates/submenuIndexImport.template%#
|
|
|
|
|
|
<h2>Index Export</h2>
|
|
<p>The local index currently contains #[ucount]# documents, only #[ucount200]# exportable with status code 200 - the remaining are error documents.</p>
|
|
|
|
#(lurlexport)#::
|
|
<form action="IndexExport_p.html" method="post" enctype="multipart/form-data" accept-charset="UTF-8">
|
|
<fieldset><legend>Loaded URL Export</legend>
|
|
<dl>
|
|
<dt class="TableCellDark">Export Path</dt>
|
|
<dd><input type="text" name="exportfilepath" value="#[exportfilepath]#" size="120" maxlength="250" />
|
|
</dd>
|
|
<dt class="TableCellDark">URL Filter</dt>
|
|
<dd><input type="text" name="exportfilter" value=".*.*" size="20" maxlength="250" />
|
|
</dd>
|
|
<dt class="TableCellDark">query</dt>
|
|
<dd><input type="text" name="exportquery" value="*:*" size="20" maxlength="250" />
|
|
</dd>
|
|
<dt class="TableCellDark">maximum age (seconds, -1 = unlimited)</dt>
|
|
<dd><input type="text" name="exportmaxseconds" value="-1" size="20" maxlength="250" />
|
|
</dd>
|
|
<dt class="TableCellDark">Export Format</dt>
|
|
<dd>
|
|
<dl>
|
|
<dt>Full Data Records:</dt>
|
|
<dd><input type="radio" name="format" value="full-solr" /> XML (Rich and full-text Solr data, one document per line in one large xml file, can be processed with shell tools, can be imported with DATA/SURROGATE/in/)<br />
|
|
<input type="radio" name="format" value="full-elasticsearch" checked="checked" /> JSON (Rich and full-text Elasticsearch data, one document per line in one flat JSON file, can be bulk-imported to elasticsearch with the command "curl -XPOST localhost:9200/collection1/yacy/_bulk --data-binary @yacy_dump_XXX.flatjson")<br />
|
|
<input type="radio" name="format" value="full-rss" /> XML (RSS)</dd>
|
|
<dt>Full URL List:</dt>
|
|
<dd><input type="radio" name="format" value="url-text" /> Plain Text List (URLs only)<br />
|
|
<input type="radio" name="format" value="url-html" /> HTML (URLs with title)</dd>
|
|
<dt>Only Domain:</dt>
|
|
<dd><input type="radio" name="format" value="dom-text" /> Plain Text List (domains only)<br />
|
|
<input type="radio" name="format" value="dom-html" /> HTML (domains as URLs, no title)</dd>
|
|
<dt>Only Text:</dt>
|
|
<dd><input type="radio" name="format" value="text-text" /> Fulltext of Search Index Text</dd>
|
|
</dl>
|
|
</dd>
|
|
<dt> </dt>
|
|
<dd><input type="submit" name="lurlexport" value="Export" class="btn btn-primary" style="width:240px;"/>
|
|
</dd>
|
|
</dl>
|
|
</fieldset>
|
|
</form>::
|
|
<div class="alert alert-info" style="text-decoration:blink">Export to file #[exportfile]# is running .. #[urlcount]# Documents so far</div>::
|
|
#(/lurlexport)#
|
|
|
|
#(lurlexportfinished)#::
|
|
<div class="alert alert-success">Finished export of #[urlcount]# Documents to file <a href="file://#[exportfile]#" target="_">#[exportfile]#</a><br/>
|
|
<em>Import this file by moving it to DATA/SURROGATES/in</em></div>::
|
|
#(/lurlexportfinished)#
|
|
|
|
#(lurlexporterror)#::
|
|
<div class="alert alert-warning">Export to file #[exportfile]# failed: #[exportfailmsg]#</div>::
|
|
#(/lurlexporterror)#
|
|
|
|
#(dumprestore)#::
|
|
<form action="IndexExport_p.html" method="post" enctype="multipart/form-data" accept-charset="UTF-8">
|
|
<fieldset><legend>Dump and Restore of Solr Index</legend>
|
|
#(dumpRestoreEnabled)#<div class="alert alert-info">This feature is available only when a local embedded Solr is active.</div>::#(/dumpRestoreEnabled)#
|
|
<dl>
|
|
<dt> </dt>
|
|
<dd><input type="submit" name="indexdump" value="Create Dump" class="btn btn-primary" style="width:240px;" #(dumpRestoreEnabled)#disabled="disabled"::#(/dumpRestoreEnabled)#/>
|
|
</dd>
|
|
</dl>
|
|
<dl>
|
|
<dt class="TableCellDark">Dump File</dt>
|
|
<dd><input type="text" name="dumpfile" value="#[dumpfile]#" size="80" maxlength="250" #(dumpRestoreEnabled)#disabled="disabled"::#(/dumpRestoreEnabled)#/>
|
|
</dd>
|
|
<dt> </dt>
|
|
<dd><input type="submit" name="indexrestore" value="Restore Dump" class="btn btn-primary" style="width:240px;" #(dumpRestoreEnabled)#disabled="disabled"::#(/dumpRestoreEnabled)#/>
|
|
</dd>
|
|
</dl>
|
|
</fieldset>
|
|
</form>::
|
|
#(/dumprestore)#
|
|
|
|
#(indexdump)#::
|
|
<div class="alert alert-success" role="alert">Stored a solr dump to file #[dumpfile]#</div>::
|
|
<div class="alert alert-danger" role="alert">Could not create the Solr dump : no embedded Solr is available.</div>::
|
|
<div class="alert alert-danger" role="alert">An error occurred while trying to create the Solr dump.</div>
|
|
#(/indexdump)#
|
|
|
|
#(indexRestore)#::
|
|
<div class="alert alert-success" role="alert">Successfully restored Solr index from dump file!</div>::
|
|
<div class="alert alert-danger" role="alert">Could not restore the Solr dump : no embedded Solr is available.</div>::
|
|
<div class="alert alert-danger" role="alert">An error occurred while trying to restore the Solr dump.</div>
|
|
#(/indexRestore)#
|
|
|
|
#%env/templates/footer.template%#
|
|
</body>
|
|
</html>
|