yacy_search_server/htroot/HostBrowser.html

261 lines
13 KiB
HTML
Raw Normal View History

2012-09-21 15:48:40 +02:00
<!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">
<head>
<title>YaCy '#[clientname]#': Index Browser</title>
2012-09-21 15:48:40 +02:00
#%env/templates/metas.template%#
<script type="text/javascript">
//<![CDATA[
function xmlhttpPost() {
var searchform = document.getElementById('searchform');
search(searchform.path.value);
2012-09-21 15:48:40 +02:00
}
function search(query) {
var xmlHttpReq = false;
var self = this;
if (window.XMLHttpRequest) { // Mozilla/Safari
self.xmlHttpReq = new XMLHttpRequest();
}
else if (window.ActiveXObject) { // IE
self.xmlHttpReq = new ActiveXObject("Microsoft.XMLHTTP");
}
self.xmlHttpReq.open('GET', "/solr/select?q=sku:\"" + query + "\" OR host_s:\"" + query + "\" OR host_dnc_s:\"" + query + "\" OR host_organization_s:\"" + query + "\" OR host_organizationdnc_s:\"" + query + "\" OR host_subdomain_s:\"" + query + "\" OR url_paths_sxt:\"" + query + "\" OR url_file_name_s:\"" + query + "\"&start=0&rows=100&wt=yjson", true);
2012-09-21 15:48:40 +02:00
self.xmlHttpReq.setRequestHeader('Content-Type', 'application/x-www-form-urlencoded');
self.xmlHttpReq.onreadystatechange = function() {
if (self.xmlHttpReq.readyState == 4) {
updatepage(self.xmlHttpReq.responseText);
}
}
self.xmlHttpReq.send(null);
}
function updatepage(str) {
var rsp = eval("("+str+")");
var firstChannel = rsp.channels[0];
var totalResults = firstChannel.totalResults.replace(/[,.]/,"");
var startIndex = firstChannel.startIndex;
var itemsPerPage = firstChannel.itemsPerPage;
var navigation = firstChannel.navigation;
var html = "";
if (totalResults > 0 && firstChannel.items.length > 0) {
var item;
html += "<table class=\"networkTable\" border=\"0\" cellpadding=\"2\" cellspacing=\"1\" width=\"99%\">";
html += "<tr class=\"TableHeader\" valign=\"bottom\">";
html += "<td>URL from index (total results = " + totalResults + ")<\/td>";
for (var i = 0; i < firstChannel.items.length; i++) {
item = firstChannel.items[i];
html += "<tr class=\"TableCellLight\"><td align=\"left\"><a href=\"HostBrowser.html?admin=#[admin]#&pathsearch=&amp;path=" + item.link + "\">" + item.link + "<\/a><\/td>";
2012-09-21 15:48:40 +02:00
}
html += "<\/table>";
}
document.getElementById("searchresults").innerHTML = html;
}
//]]>
</script>
<script type="text/javascript" src="js/sorttable.js"></script>
<!-- style for hypertree -->
<link href="env/hypertree.css" rel="stylesheet">
2012-09-21 15:48:40 +02:00
</head>
<body id="IndexControl">
#(topmenu)#
<div class="SubMenu">
<ul class="SubMenu">
<li style="width:15%;"><a class="MenuItemLink" href="index.html"><img src="env/grafics/navsl.gif" height="10px" style="padding-right:10px" align="baseline"/>back to start page</a></li>
</ul>
</div>
#%env/templates/embeddedheader.template%#
::
#%env/templates/simpleheader.template%#
<script type="text/javascript">
document.getElementById("header_hostbrowser").className += " active";
</script>
::
#%env/templates/header.template%#
#%env/templates/submenuWebStructure.template%#
#(/topmenu)#
<h2>Index Browser</h2>
<p>Browse the index of #[ucount]# documents. Enter a host or an URL for a file list or view a list of <a href="HostBrowser.html?admin=#[admin]#&hosts=">all hosts</a>, <a href="HostBrowser.html?admin=#[admin]#&hosts=crawling">only hosts with urls pending in the crawler</a> or <a href="HostBrowser.html?admin=#[admin]#&hosts=error">only with load errors</a>.</p>
<form action="HostBrowser.html" id="searchform" method="get" onkeyup="xmlhttpPost(); return false;">
<fieldset class="yacys">
<input type="hidden" name="admin" id="admin" value="#[admin]#" />
<div class="input-group" style="width:600px;float:left;">
<span class="input-group-addon">Host/URL</span>
<input id="search" type="text" name="path" value="#[path]#" maxlength="250" class="form-control"/>
<div class="input-group-btn">
<button id="list" name="list" class="btn btn-primary">Browse Host</button>
</div>
</div>
#(delete)#::
&nbsp;<input type="submit" name="delete" value="Delete Subpath" class="btn btn-danger" onclick="return confirm('Confirm Deletion')"/>
<input type="submit" name="reload404" value="Re-load load-failure docs (404s etc)" class="btn btn-warning" />
#(/delete)#
<div id="searchresults" style="clear:both;"></div>
2012-09-21 15:48:40 +02:00
</fieldset>
</form>
#[result]#
2012-09-21 15:48:40 +02:00
#(hosts)#::
<fieldset><legend>Host List</legend>
#{list}#
<div style="float:left; padding:1px 5px 1px 5px;">
<div style="width:180px; text-align:left; float: left; white-space:nowrap; overflow:hidden;"><div id="info"><img src="env/grafics/#(type)#invisible.png::burn-e.gif::construction.gif#(/type)#" align="left" width="12" height="8">&nbsp;<a href="HostBrowser.html?admin=#[admin]#&path=#[host]#&facetcount=#[count]#">#[host]#</a></div></div>
<div style="width:120px; text-align:right; float: left; white-space:nowrap; overflow:hidden;"><span class="commit">#[count]#</span>#(crawler)#::/<span class="pending">#[pending]#</span>#(/crawler)##(errors)#::/<span class="info">#[exclcount]#</span>/<span class="error">#[failcount]#</span>#(/errors)# URLs</div>
</div>
#{/list}#
<div style="clear:both; float:left; padding:10px 5px 1px 5px;">
<div style="float:left;clear:both;">Count Colors:</div>
<div class="commit" style="float:left;">&nbsp;&nbsp;&nbsp;Documents without Errors</div>
<div class="pending" style="float:left;">&nbsp;&nbsp;&nbsp;Pending in Crawler</div>
<div class="info" style="float:left;">&nbsp;&nbsp;&nbsp;Crawler Excludes</div>
<div class="error" style="float:left;">&nbsp;&nbsp;&nbsp;Load Errors</div>
</div>
</fieldset>
added a new way of content browsing in search results: - date navigation The date is taken from the CONTENT of the documents / web pages, NOT from a date submitted in the context of metadata (i.e. http header or html head form). This makes it possible to search for documents in the future, i.e. when documents contain event descriptions for future events. The date is written to an index field which is now enabled by default. All documents are scanned for contained date mentions. To visualize the dates for a specific search results, a histogram showing the number of documents for each day is displayed. To render these histograms the morris.js library is used. Morris.js requires also raphael.js which is now also integrated in YaCy. The histogram is now also displayed in the index browser by default. To select a specific range from a search result, the following modifiers had been introduced: from:<date> to:<date> These modifiers can be used separately (i.e. only 'from' or only 'to') to describe an open interval or combined to have a closed interval. Both dates are inclusive. To select a specific single date only, use the 'to:' - modifier. The histogram shows blue and green lines; the green lines denot weekend days (saturday and sunday). Clicking on bars in the histogram has the following reaction: 1st click: add a from:<date> modifier for the date of the bar 2nd click: add a to:<date> modifier for the date of the bar 3rd click: remove from and date modifier and set a on:<date> for the bar When the on:<date> modifier is used, the histogram shows an unlimited time period. This makes it possible to click again (4th click) which is then interpreted as a 1st click again (sets a from modifier). The display feature is NOT switched on by default; to switch it on use the /ConfigSearchPage_p.html servlet.
2015-03-02 04:30:10 +01:00
<link rel="stylesheet" href="/env/morris.css">
<script src="/js/raphael-min.js"></script>
<script src="/js/morris.js"></script>
<div id="graph" style="height:200px"></div>
<script>
2015-03-02 04:43:42 +01:00
var solr= $.getJSON("/solr/collection1/select?q=*:*&defType=edismax&start=0&rows=0&wt=json&facet=true&facet.field=dates_in_content_dts&facet.sort=index", function(data) {
added a new way of content browsing in search results: - date navigation The date is taken from the CONTENT of the documents / web pages, NOT from a date submitted in the context of metadata (i.e. http header or html head form). This makes it possible to search for documents in the future, i.e. when documents contain event descriptions for future events. The date is written to an index field which is now enabled by default. All documents are scanned for contained date mentions. To visualize the dates for a specific search results, a histogram showing the number of documents for each day is displayed. To render these histograms the morris.js library is used. Morris.js requires also raphael.js which is now also integrated in YaCy. The histogram is now also displayed in the index browser by default. To select a specific range from a search result, the following modifiers had been introduced: from:<date> to:<date> These modifiers can be used separately (i.e. only 'from' or only 'to') to describe an open interval or combined to have a closed interval. Both dates are inclusive. To select a specific single date only, use the 'to:' - modifier. The histogram shows blue and green lines; the green lines denot weekend days (saturday and sunday). Clicking on bars in the histogram has the following reaction: 1st click: add a from:<date> modifier for the date of the bar 2nd click: add a to:<date> modifier for the date of the bar 3rd click: remove from and date modifier and set a on:<date> for the bar When the on:<date> modifier is used, the histogram shows an unlimited time period. This makes it possible to click again (4th click) which is then interpreted as a 1st click again (sets a from modifier). The display feature is NOT switched on by default; to switch it on use the /ConfigSearchPage_p.html servlet.
2015-03-02 04:30:10 +01:00
dates_in_content_dts = data.facet_counts.facet_fields.dates_in_content_dts;
var parsed = [];
for (var i = 0; i < dates_in_content_dts.length; i = i + 2) {
var date = dates_in_content_dts[i];
var count = dates_in_content_dts[i + 1];
if (date && count) {parsed[parsed.length] = {x: date,y: count};};
};
if (parsed.length > 0) Morris.Bar({
element: 'graph',
data: parsed,
xkey: 'x',
ykeys: ['y'],
labels: ['number of documents about this date'],
yLabelFormat: function (y) { return y.toString() + ' docs'; },
barColors: function (row, series, type) {
var d = new Date(row.label);
if (d.getDay() === 6) return '#4aaf46'; //saturday
if (d.getDay() === 0) return '#4aaf46'; //sunday
return '#3574c0';
},
hideHover: 'false'
}).on('click', function(i, row) {
console.log(i, row);
});
});
</script>
#(/hosts)#
2012-09-21 15:48:40 +02:00
#(hostanalysis)#::
<fieldset><legend>Host Analysis</legend>
#{facets}#
<table class="sortable" border="0" style="float:left">
<tr class="TableCellDark">
<td align="left" colspan="5" nowrap class="pending">#[facetname]#</td>
<td align="right" colspan="5" nowrap class="listingok">#</td>
</tr>
#{facet}#
<tr class="TableCellLight">
<td align="left" colspan="5" nowrap class="pending">#[key]#</td>
<td align="right" colspan="5" nowrap class="listingok"><a href="#[a]#" target="_blank" class="forceNoExternalIcon">#[count]#</a></td>
</tr>
#{/facet}#
</table>&nbsp;&nbsp;
#{/facets}#
</fieldset>
#(/hostanalysis)#
#(files)#::
<fieldset><legend>Browser for <a href="#[path]#" target="_blank">#[path]#</a></legend>
<p>documents stored for host: #[hostsize]#; documents stored for subpath: #[subpathloadsize]#; unloaded documents detected in subpath: #[subpathdetectedsize]# <!-- #(complete)#;<a href="HostBrowser.html?admin=#[admin]#&complete=true&path=#[path]#">get complete list</a>::<a href="HostBrowser.html?admin=#[admin]#&path=#[path]#">directory view</a>#(/complete)#-->
</p>
<table class="sortable" border="0" style="float:left">
<tr>
<th align="center" width="32"></th>
<th align="left" width="600" class="listing">Path</th>
<td align="right" class="listingem">stored</td>
<td align="right" class="listingem">linked</td>
<td align="right" class="listingem">pending</td>
<td align="right" class="listingem">excluded</td>
<td align="right" class="listingem">failed</td>
</tr>
#(root)#
<tr class="TableCell#(dark)#Light::Dark::Summary#(/dark)#">
<td align="center"></td>
<td align="left" nowrap ><a href="HostBrowser.html?admin=#[admin]#&path=#[path]#" class="listing">..</a></td>
<td align="right" colspan="5" nowrap></td>
</tr>::
#(/root)#
#{list}#
#(type)#<!--file-->
<tr class="TableCell#(dark)#Light::Dark::Summary#(/dark)#">
<td align="center"><div id="info"><a href="ViewFile.html?url=#[url]#"><img src="env/grafics/doc.gif"/></a><span>Show Metadata</span></div></td>
<td align="left" nowrap class=#(stored)#"listingem"::"listing"#(/stored)#><a href="#[url]#" target="_blank">#[url]#</a></td>
#(stored)#
#(load)#<td align="left" colspan="5" nowrap class="listingem">link, detected from context</td>::<td align="left" colspan="5" nowrap class="listingnok"><a href="HostBrowser.html?admin=#[admin]#&load=#[url]#&path=#[path]#">load &amp; index</a>#(/load)#</td>::
<td align="left" colspan="1" nowrap class="listingok">indexed</td><td align="left" colspan="4" nowrap class="listingem">#[comment]#</td>::
<td align="left" colspan="5" nowrap class="pending">loading</td>::
<td align="left" colspan="5" nowrap class="listingnok">#[error]#</td>
#(/stored)#
</tr>::<!--folder-->
<tr class="TableCell#(dark)#Light::Dark::Summary#(/dark)#">
<td align="center"><img src="env/grafics/dir.gif"/></td>
<td align="left" nowrap class="listing"><a href="HostBrowser.html?admin=#[admin]#&path=#[url]#" class="listing">#[url]#</a></td>
<td align="right" class="commit">#[stored]#</td>
<td align="right" class="listing">#[linked]#</td>
<td align="right" #(pendingVisible)#class="listingem"::class="pending"#(/pendingVisible)#>#[pending]#</td>
<td align="right" #(excludedVisible)#class="listingem"::class="error"#(/excludedVisible)#>#[excluded]#</td>
<td align="right" #(failedVisible)#class="listingem"::class="error"#(/failedVisible)#>#[failed]#</td>
</tr>
#(/type)#
#{/list}#
</table>
</fieldset>
#(linkgraph)#<div align="center"><form><input name="showlinkstructure" onClick="location.href = location.toString() + '&showlinkstructure=';" class="btn btn-default btn-xs" value="show link structure graph"/></form></div>::
<script src="/js/d3.v3.min.js"></script>
<script src="/js/hypertree.js"></script>
<div id="linkstructure"></div>
<script>$(document).ready(linkstructure("#[host]#", "#linkstructure", 1280, 720, 3000, 700));</script>
#(/linkgraph)#
#(/files)#
#(outbound)#::
<fieldset><legend>Outbound Links, outgoing from #[host]# - Host List</legend>
#{list}#
<div style="float:left; padding:1px 5px 1px 5px;">
<div style="width:160px; text-align:left; float: left; white-space:nowrap; overflow:hidden;"><div id="info"><a href="HostBrowser.html?admin=#[admin]#&path=#[link]#">#[host]#</a></div></div>
<div style="width:80px; text-align:right; float: left; white-space:nowrap; overflow:hidden;">#[count]# URLs</div>
</div>
#{/list}#
#(admin)#::
<p style="clear:both"><br/>
<img src="WebStructurePicture_p.png?host=#[host]#&depth=3&width=1024&height=576&nodes=200&time=1000&colortext=888888&colorback=FFFFFF&colordot0=1111BB&colordota=11BB11&colorline=222222&colorlineend=333333">
</p>
#(/admin)#
</fieldset>
#(/outbound)#
#(inbound)#::
<fieldset><legend>Inbound Links, incoming to #[host]# - Host List</legend>
#{list}#
<div style="float:left; padding:1px 5px 1px 5px;">
<div style="width:160px; text-align:left; float: left; white-space:nowrap; overflow:hidden;"><div id="info"><a href="HostBrowser.html?admin=#[admin]#&path=#[host]#">#[host]#</a></div></div>
<div style="width:80px; text-align:right; float: left; white-space:nowrap; overflow:hidden;">#[count]# URLs</div>
</div>
#{/list}#
</fieldset>
#(/inbound)#
#(admin)#::
#%HostBrowserAdmin_p.html%#
#(/admin)#
2012-09-21 15:48:40 +02:00
#%env/templates/footer.template%#
</body>
</html>