Menu
▾
▴
archive-access-cvs — CVS commits
You can subscribe to this list here.
| 2005 |
Jan
|
Feb
|
Mar
|
Apr
|
May
|
Jun
|
Jul
(1) |
Aug
(10) |
Sep
(36) |
Oct
(339) |
Nov
(103) |
Dec
(152) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2006 |
Jan
(141) |
Feb
(102) |
Mar
(125) |
Apr
(203) |
May
(57) |
Jun
(30) |
Jul
(139) |
Aug
(46) |
Sep
(64) |
Oct
(105) |
Nov
(34) |
Dec
(162) |
| 2007 |
Jan
(81) |
Feb
(57) |
Mar
(141) |
Apr
(72) |
May
(9) |
Jun
(1) |
Jul
(144) |
Aug
(88) |
Sep
(40) |
Oct
(43) |
Nov
(34) |
Dec
(20) |
| 2008 |
Jan
(44) |
Feb
(45) |
Mar
(16) |
Apr
(36) |
May
(8) |
Jun
(77) |
Jul
(177) |
Aug
(66) |
Sep
(8) |
Oct
(33) |
Nov
(13) |
Dec
(37) |
| 2009 |
Jan
(2) |
Feb
(5) |
Mar
(8) |
Apr
|
May
(36) |
Jun
(19) |
Jul
(46) |
Aug
(8) |
Sep
(1) |
Oct
(66) |
Nov
(61) |
Dec
(10) |
| 2010 |
Jan
(13) |
Feb
(16) |
Mar
(38) |
Apr
(76) |
May
(47) |
Jun
(32) |
Jul
(35) |
Aug
(45) |
Sep
(20) |
Oct
(61) |
Nov
(24) |
Dec
(16) |
| 2011 |
Jan
(22) |
Feb
(34) |
Mar
(11) |
Apr
(8) |
May
(24) |
Jun
(23) |
Jul
(11) |
Aug
(42) |
Sep
(81) |
Oct
(48) |
Nov
(21) |
Dec
(20) |
| 2012 |
Jan
(30) |
Feb
(25) |
Mar
(4) |
Apr
(6) |
May
(1) |
Jun
(5) |
Jul
(5) |
Aug
(8) |
Sep
(6) |
Oct
(6) |
Nov
|
Dec
|
Revision: 3180
http://archive-access.svn.sourceforge.net/archive-access/?rev=3180&view=rev
Author: bradtofel
Date: 2010-07-20 23:52:12 +0000 (Tue, 20 Jul 2010)
Log Message:
-----------
TWEAK: somewhat undoing wrapper code, at least allowing it to be optional
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/exception/BaseExceptionRenderer.java
Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/exception/BaseExceptionRenderer.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/exception/BaseExceptionRenderer.java 2010-07-20 23:51:47 UTC (rev 3179)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/exception/BaseExceptionRenderer.java 2010-07-20 23:52:12 UTC (rev 3180)
@@ -142,8 +142,13 @@
}
}
if(!handled) {
- uiResults.forwardWrapped(httpRequest, httpResponse,
- errorJsp, wbRequest.getAccessPoint().getWrapperJsp());
+ String wrapperJsp = wbRequest.getAccessPoint().getWrapperJsp();
+ if(wrapperJsp != null) {
+ uiResults.forwardWrapped(httpRequest, httpResponse,
+ errorJsp, wrapperJsp);
+ } else {
+ uiResults.forward(httpRequest, httpResponse, errorJsp);
+ }
}
}
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bra...@us...> - 2010-07-20 23:51:54
|
Revision: 3179
http://archive-access.svn.sourceforge.net/archive-access/?rev=3179&view=rev
Author: bradtofel
Date: 2010-07-20 23:51:47 +0000 (Tue, 20 Jul 2010)
Log Message:
-----------
BUGFIX: was not properly setting the User-Agent on output requests
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/liveweb/URLtoARCCacher.java
Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/liveweb/URLtoARCCacher.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/liveweb/URLtoARCCacher.java 2010-07-20 23:50:57 UTC (rev 3178)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/liveweb/URLtoARCCacher.java 2010-07-20 23:51:47 UTC (rev 3179)
@@ -88,7 +88,8 @@
manager.getParams().setSoTimeout(socketTimeoutMS);
http.setHttpConnectionManager(manager);
HttpClientParams clientParams = new HttpClientParams();
- clientParams.setParameter("http.useragent", userAgent);
+// LOGGER.warn("Setting HTTP UserAgent to " + userAgent);
+// clientParams.setParameter("http.useragent", userAgent);
return http;
}
};
@@ -135,6 +136,7 @@
HttpClient client = getHttpClient();
getMethod.getParams().setCookiePolicy(CookiePolicy.IGNORE_COOKIES);
getMethod.setFollowRedirects(false);
+ getMethod.setRequestHeader("User-Agent", userAgent);
int code = client.executeMethod(getMethod);
LOGGER.info("URL(" + url + ") HTTP:" + code);
ByteOp.discardStream(getMethod.getResponseBodyAsStream());
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bra...@us...> - 2010-07-20 23:51:03
|
Revision: 3178
http://archive-access.svn.sourceforge.net/archive-access/?rev=3178&view=rev
Author: bradtofel
Date: 2010-07-20 23:50:57 +0000 (Tue, 20 Jul 2010)
Log Message:
-----------
TWEAK: somewhat undoing wrapper code, at least allowing it to be optional
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/query/Renderer.java
Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/query/Renderer.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/query/Renderer.java 2010-07-20 23:50:10 UTC (rev 3177)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/query/Renderer.java 2010-07-20 23:50:57 UTC (rev 3178)
@@ -61,8 +61,13 @@
if(wbRequest.isXMLMode()) {
uiResults.forward(httpRequest, httpResponse, xmlCaptureJsp);
} else {
- uiResults.forwardWrapped(httpRequest, httpResponse,
- captureJsp, wbRequest.getAccessPoint().getWrapperJsp());
+ String wrapperJsp = wbRequest.getAccessPoint().getWrapperJsp();
+ if(wrapperJsp != null) {
+ uiResults.forwardWrapped(httpRequest, httpResponse,
+ captureJsp, wrapperJsp);
+ } else {
+ uiResults.forward(httpRequest, httpResponse, captureJsp);
+ }
}
}
@@ -78,8 +83,14 @@
if(wbRequest.isXMLMode()) {
uiResults.forward(httpRequest, httpResponse, xmlUrlJsp);
} else {
- uiResults.forwardWrapped(httpRequest, httpResponse,
- urlJsp,wbRequest.getAccessPoint().getWrapperJsp());
+ String wrapperJsp = wbRequest.getAccessPoint().getWrapperJsp();
+ if(wrapperJsp != null) {
+
+ uiResults.forwardWrapped(httpRequest, httpResponse,
+ urlJsp,wbRequest.getAccessPoint().getWrapperJsp());
+ } else {
+ uiResults.forward(httpRequest, httpResponse, urlJsp);
+ }
}
}
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bra...@us...> - 2010-07-20 23:50:17
|
Revision: 3177
http://archive-access.svn.sourceforge.net/archive-access/?rev=3177&view=rev
Author: bradtofel
Date: 2010-07-20 23:50:10 +0000 (Tue, 20 Jul 2010)
Log Message:
-----------
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/exception/HTMLError.jsp
Modified: trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/exception/HTMLError.jsp
===================================================================
--- trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/exception/HTMLError.jsp 2010-07-20 23:49:44 UTC (rev 3176)
+++ trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/exception/HTMLError.jsp 2010-07-20 23:50:10 UTC (rev 3177)
@@ -36,7 +36,7 @@
<div id="positionHome">
<section>
<div id="logoHome">
- <h1><span>Internet Archive's Wayback Machine</span></h1>
+ <a href="/index.jsp"><h1><span>Internet Archive's Wayback Machine</span></h1></a>
</div>
</section>
<section>
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
Revision: 3176
http://archive-access.svn.sourceforge.net/archive-access/?rev=3176&view=rev
Author: bradtofel
Date: 2010-07-20 23:49:44 +0000 (Tue, 20 Jul 2010)
Log Message:
-----------
FEATURE: add CaptureSearchResults to the exception if the problem is ResourceNotAvailable, allowing jsp to offer alternate versions.
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/exception/ResourceNotAvailableException.java
Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/exception/ResourceNotAvailableException.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/exception/ResourceNotAvailableException.java 2010-07-20 23:48:56 UTC (rev 3175)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/exception/ResourceNotAvailableException.java 2010-07-20 23:49:44 UTC (rev 3176)
@@ -26,6 +26,9 @@
import javax.servlet.http.HttpServletResponse;
+import org.archive.wayback.core.CaptureSearchResults;
+import org.archive.wayback.core.SearchResults;
+
/**
* Exception class for queries which matching resource is not presently
* accessible
@@ -39,6 +42,7 @@
*/
private static final long serialVersionUID = 1L;
protected static final String ID = "resourceNotAvailable";
+ private CaptureSearchResults results;
/**
* Constructor
@@ -65,4 +69,13 @@
public int getStatus() {
return HttpServletResponse.SC_SERVICE_UNAVAILABLE;
}
+ /**
+ * @param results
+ */
+ public void setCaptureSearchResults(CaptureSearchResults results) {
+ this.results = results;
+ }
+ public CaptureSearchResults getCaptureSearchResults() {
+ return results;
+ }
}
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bra...@us...> - 2010-07-20 23:49:02
|
Revision: 3175
http://archive-access.svn.sourceforge.net/archive-access/?rev=3175&view=rev
Author: bradtofel
Date: 2010-07-20 23:48:56 +0000 (Tue, 20 Jul 2010)
Log Message:
-----------
FEATURE: add CaptureSearchResults to the exception if the problem is ResourceNotAvailable, allowing jsp to offer alternate versions.
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/webapp/AccessPoint.java
Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/webapp/AccessPoint.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/webapp/AccessPoint.java 2010-07-20 19:17:09 UTC (rev 3174)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/webapp/AccessPoint.java 2010-07-20 23:48:56 UTC (rev 3175)
@@ -329,8 +329,13 @@
CaptureSearchResult closest = captureResults.getClosest(wbRequest,
isUseAnchorWindow());
closest.setClosest(true);
- resource =
- getCollection().getResourceStore().retrieveResource(closest);
+ try {
+ resource =
+ getCollection().getResourceStore().retrieveResource(closest);
+ } catch (ResourceNotAvailableException rnae) {
+ rnae.setCaptureSearchResults((CaptureSearchResults)results);
+ throw rnae;
+ }
p.retrieved();
ReplayRenderer renderer =
getReplay().getRenderer(wbRequest, closest, resource);
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bra...@us...> - 2010-07-20 19:17:16
|
Revision: 3174
http://archive-access.svn.sourceforge.net/archive-access/?rev=3174&view=rev
Author: bradtofel
Date: 2010-07-20 19:17:09 +0000 (Tue, 20 Jul 2010)
Log Message:
-----------
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/query/HTMLUrlResults.jsp
Modified: trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/query/HTMLUrlResults.jsp
===================================================================
--- trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/query/HTMLUrlResults.jsp 2010-07-19 23:47:20 UTC (rev 3173)
+++ trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/query/HTMLUrlResults.jsp 2010-07-20 19:17:09 UTC (rev 3174)
@@ -32,12 +32,10 @@
long totalCaptures = uResults.getMatchingCount();
%>
-<script src="http://ajax.googleapis.com/ajax/libs/jquery/1.4.2/jquery.min.js" type="text/javascript"></script>
-<script src="http://ajax.googleapis.com/ajax/libs/jqueryui/1.8.1/jquery-ui.min.js" type="text/javascript"></script>
+<script type="text/javascript" src="<%= staticPrefix %>js/jquery-1.4.2.min.js"></script>
<script type="text/javascript" src="<%= staticPrefix %>js/jquery.dataTables.min.js" charset="utf-8"></script>
<script type="text/javascript">
$().ready(function(){
- $(".dataTables_processing").show();
$('#resultsUrl th.url span').html(' ↑');
$('#resultsUrl th').mouseup(function(){
\$('#resultsUrl th span').html('');
@@ -81,14 +79,11 @@
});
}
});
-$(window).load(function(){
-
-});
</script>
<div id="positionHome">
<section>
<div id="logoHome">
- <h1><span>Internet Archive's Wayback Machine</span></h1>
+ <a href="/index.jsp"><h1><span>Internet Archive's Wayback Machine</span></h1></a>
</div>
</section>
<section>
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bra...@us...> - 2010-07-19 23:47:26
|
Revision: 3173
http://archive-access.svn.sourceforge.net/archive-access/?rev=3173&view=rev
Author: bradtofel
Date: 2010-07-19 23:47:20 +0000 (Mon, 19 Jul 2010)
Log Message:
-----------
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/query/BubbleCalendar.jsp
Modified: trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/query/BubbleCalendar.jsp
===================================================================
--- trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/query/BubbleCalendar.jsp 2010-07-19 23:45:08 UTC (rev 3172)
+++ trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/query/BubbleCalendar.jsp 2010-07-19 23:47:20 UTC (rev 3173)
@@ -139,16 +139,16 @@
var actualsize = $(this).find(".hidden").text();
var size = actualsize * 12;
var offset = size / 2;
- if (actualsize == 1) {size = 20, offset = 10;}
- else if (actualsize == 2) {size = 30, offset = 15;}
- else if (actualsize == 3) {size = 40, offset = 20;}
- else if (actualsize == 4) {size = 50, offset = 25;}
- else if (actualsize == 5) {size = 60, offset = 30;}
- else if (actualsize == 6) {size = 70, offset = 35;}
- else if (actualsize == 7) {size = 80, offset = 40;}
- else if (actualsize == 8) {size = 90, offset = 45;}
- else if (actualsize == 9) {size = 100, offset = 50;}
- else if (actualsize >= 10) {size = 110, offset = 55;}
+ if (actualsize == 1) {size = 30, offset = 15;}
+ else if (actualsize == 2) {size = 40, offset = 20;}
+ else if (actualsize == 3) {size = 50, offset = 25;}
+ else if (actualsize == 4) {size = 60, offset = 30;}
+ else if (actualsize == 5) {size = 70, offset = 35;}
+ else if (actualsize == 6) {size = 80, offset = 40;}
+ else if (actualsize == 7) {size = 90, offset = 45;}
+ else if (actualsize == 8) {size = 100, offset = 50;}
+ else if (actualsize == 9) {size = 110, offset = 55;}
+ else if (actualsize >= 10) {size = 120, offset = 60;}
$(this).find("img").attr("src","<%= staticPrefix %>images/blueblob-dk.png");
$(this).find(".measure").css({'width':+size+'px','height':+size+'px','top':'-'+offset+'px','left':'-'+offset+'px'});
});
@@ -163,22 +163,22 @@
$(".tooltip").bt({
positions: ['top','right','left','bottom'],
contentSelector: "$(this).find('.pop').html()",
- padding: '0',
- width: '145px',
- spikeGirth: 12,
- spikeLength: 12,
- overlap: '2px',
+ padding: 0,
+ width: '115px',
+ spikeGirth: 8,
+ spikeLength: 8,
+ overlap: 0,
cornerRadius: 5,
fill: '#efefef',
strokeWidth: 1,
strokeStyle: '#efefef',
shadow: true,
shadowColor: '#333',
- shadowBlur: 6,
+ shadowBlur: 5,
shadowOffsetX: 0,
shadowOffsetY: 0,
noShadowOpts: {strokeStyle:'#ccc'},
- hoverIntentOpts: {interval:0,timeout:4000},
+ hoverIntentOpts: {interval:60,timeout:3500},
clickAnywhereToClose: true,
closeWhenOthersOpen: true,
windowMargin: 30,
@@ -190,9 +190,7 @@
color: '#333'
}
});
-});
-$().ready(function(){
var yrCount = $(".wbChartThisContainer").size();
var yrTotal = <%= yearWidth %> * yrCount;
var yrPad = (930 - yrTotal) / 2;
@@ -218,8 +216,8 @@
</form>
<div id="wbMeta">
- <p class="wbThis"><a href="<%= data.searchUrlForHTML %>"><%= data.searchUrlForHTML %></a> has been crawled <strong><%= fmt.format("{0} times",data.numResults) %></strong> going all the way back to <a href="firstcapture"><%= fmt.format("{0,date,MMM dd yyyy}",data.firstResultDate) %></a>.</p>
- <p class="wbNote">A crawl can be a duplicate of the last one. It happens about [num]% of the time across [NUM] websites. <a href="FAQ">FAQ</a></p>
+ <p class="wbThis"><a href="<%= data.searchUrlForHTML %>"><%= data.searchUrlForHTML %></a> has been crawled <strong><%= fmt.format("{0} times",data.numResults) %></strong> going all the way back to <a href="firstcapture"><%= fmt.format("{0,date,MMMM d, yyyy}",data.firstResultDate) %></a>.</p>
+ <p class="wbNote">A crawl can be a duplicate of the last one. It happens about [num]% of the time across [NUM] websites. <a href="https://webarchive.jira.com/wiki/display/WWMOS/FAQs">FAQ</a></p>
</div>
</div>
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bra...@us...> - 2010-07-19 23:45:15
|
Revision: 3172
http://archive-access.svn.sourceforge.net/archive-access/?rev=3172&view=rev
Author: bradtofel
Date: 2010-07-19 23:45:08 +0000 (Mon, 19 Jul 2010)
Log Message:
-----------
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/query/BubbleCalendar.jsp
Modified: trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/query/BubbleCalendar.jsp
===================================================================
--- trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/query/BubbleCalendar.jsp 2010-07-16 20:26:03 UTC (rev 3171)
+++ trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/query/BubbleCalendar.jsp 2010-07-19 23:45:08 UTC (rev 3172)
@@ -9,9 +9,11 @@
<%@ page import="org.archive.wayback.core.CaptureSearchResult" %>
<%@ page import="org.archive.wayback.core.CaptureSearchResults" %>
<%@ page import="org.archive.wayback.core.UIResults" %>
+<%@ page import="org.archive.wayback.core.WaybackRequest" %>
<%@ page import="org.archive.wayback.partition.BubbleCalendarData" %>
<%@ page import="org.archive.wayback.util.partition.Partition" %>
<%@ page import="org.archive.wayback.util.StringFormatter" %>
+<jsp:include page="/WEB-INF/global-template/UI-header.jsp" flush="true" />
<jsp:include page="/WEB-INF/template/CookieJS.jsp" flush="true" />
<%
UIResults results = UIResults.extractCaptureQuery(request);
@@ -31,10 +33,10 @@
}
// graph size "constants": These are currently baked-in to the JS logic...
-int imgWidth = 735;
+int imgWidth = 915;
int imgHeight = 75;
-int yearWidth = 49;
-int monthWidth = 4;
+int yearWidth = 61;
+int monthWidth = 5;
BubbleCalendarData data = new BubbleCalendarData(results);
@@ -45,8 +47,7 @@
Calendar cal = BubbleCalendarData.getUTCCalendar();
%>
-<script src="http://ajax.googleapis.com/ajax/libs/jquery/1.4.2/jquery.min.js" type="text/javascript"></script>
-<script src="http://ajax.googleapis.com/ajax/libs/jqueryui/1.8.1/jquery-ui.min.js" type="text/javascript"></script>
+<script type="text/javascript" src="<%= staticPrefix %>js/jquery-1.4.2.min.js"></script>
<script type="text/javascript" src="<%= staticPrefix %>js/excanvas.compiled.js"></script>
<script type="text/javascript" src="<%= staticPrefix %>js/jquery.bt.min.js" charset="utf-8"></script>
<script type="text/javascript" src="<%= staticPrefix %>js/jquery.hoverintent.min.js" charset="utf-8"></script>
@@ -126,7 +127,7 @@
zeroPad(monthOfYear+1,2) +
zeroPad(day,2) + "000000";
- var url = wbPrefix + dateString + '*/' + wbCurrentUrl;
+ var url = "<%= queryPrefix %>" + dateString + '*/' + wbCurrentUrl;
document.getElementById('wm-graph-anchor').href = url;
setActiveYear(year);
}
@@ -135,20 +136,29 @@
<script type="text/javascript">
$().ready(function(){
$(".date").each(function(i){
- var size = $(this).find(".hidden").text();
+ var actualsize = $(this).find(".hidden").text();
+ var size = actualsize * 12;
var offset = size / 2;
- if (size >= 1 && size <= 20) {size = 20, offset = 10;}
+ if (actualsize == 1) {size = 20, offset = 10;}
+ else if (actualsize == 2) {size = 30, offset = 15;}
+ else if (actualsize == 3) {size = 40, offset = 20;}
+ else if (actualsize == 4) {size = 50, offset = 25;}
+ else if (actualsize == 5) {size = 60, offset = 30;}
+ else if (actualsize == 6) {size = 70, offset = 35;}
+ else if (actualsize == 7) {size = 80, offset = 40;}
+ else if (actualsize == 8) {size = 90, offset = 45;}
+ else if (actualsize == 9) {size = 100, offset = 50;}
+ else if (actualsize >= 10) {size = 110, offset = 55;}
$(this).find("img").attr("src","<%= staticPrefix %>images/blueblob-dk.png");
$(this).find(".measure").css({'width':+size+'px','height':+size+'px','top':'-'+offset+'px','left':'-'+offset+'px'});
});
$(".day a").each(function(i){
var dateClass = $(this).attr("class");
var dateId = "#"+dateClass;
- $(this).hover(function(){
- $(dateId).removeClass("opacity20");
- },function(){
- $(dateId).addClass("opacity20");
- });
+ $(this).hover(
+ function(){$(dateId).removeClass("opacity20");},
+ function(){$(dateId).addClass("opacity20");}
+ );
});
$(".tooltip").bt({
positions: ['top','right','left','bottom'],
@@ -181,183 +191,7 @@
}
});
});
-</script>
-<style type="text/css">
-body,div,p,td,th,ul,ol,li {margin:0;padding:0;}
-body {background-color:#fff;font-family:"Arial","Helvetica Neue","Helvetica",sans-serif;font-size:100%;}
-img {border:none;}
-a {color:#069;}
-.clearfix{width:100%;clear:both;}
-.clearfix:after {content:".";display:block;height:0;clear:both;visibility:hidden;}
-#position {padding:0;margin:0 auto;width:990px;background-color:#fff;}
-#wbCalendar {position:relative;width:990px;margin-top:25px;}
-.calPosition {padding:15px 0 25px 25px;}
-#calUnder {overflow:hidden;}
-#calOver {position:absolute;top:0;left:0;}
-.hidden{display:none;}
-.opacity20 {
- opacity:.2;
- -ms-filter:"progid:DXImageTransform.Microsoft.Alpha(Opacity=20)";
- filter: alpha(opacity=20);
-}
-.month {
- width: 240px;
- height: 210px;
- float: left;
-}
-.month table {
- border-collapse: collapse;
- font-family: "Arial", sans-serif;
- border-spacing: 1px;
-}
-.month table th {
- font-size: 0.75em;
- font-weight: 700;
- text-transform: uppercase;
- padding: 6px;
-}
-.month table span.label {
- display: block;
- min-height: 20px;
-}
-.month table td {
- padding: 0;
- vertical-align: middle;
- color: #666;
-}
-.month table td .day {
- width: 30px;
- height: 30px;
- text-align: center;
-}
-.month table td .day a,
-.month table td .day span {
- display: block;
- font-size: 0.6875em;
- width: 30px;
- height: 22px;
- padding-top: 8px;
-}
-.month table td .day a {
- color: #000;
- font-weight: 700;
- text-decoration: none;
-}
-.month table td .day span {
- padding-top: 9px;
- height: 19px;
-}
-.month table td .day a:hover {
- font-size: 0.9375em;
- padding-top: 6px;
- height: 22px;
-}
-.month table td .date {
- width: 30px;
- height: 30px;
-}
-.month table td .position {
- position: relative;
- top: 15px;
- left: 15px;
- width: 1px;
- height: 1px;
-}
-.month table td .measure {
- position: absolute;
-}
-.activeHighlight {
- background-color: #000!important;
- padding-top: 4px;
- font-size: 1.375em!important;
- color: #fff300!important;
- font-weight: normal!important;
- cursor: pointer;
-}
-.inactiveHighlight {
- background-color: #fff!important;
- padding-top: 4px;
- font-size: .75em!important;
- color: #000!important;
- font-weight: normal!important;
- cursor: pointer;
-}
-.bt-content {
- text-align: left;
-}
-.pop {display:none;}
-.bt-content h3 {font-size: 1em;font-weight: 700;text-transform: uppercase;margin:0 0 5px;}
-.bt-content p {font-size: 0.875em;margin: 5px 0;color:#666;}
-.bt-content ul {line-height:1.5em;margin:0 0 0 1em;}
-.bt-content em {color:#999;}
-.bt-content a:hover {color:#036;}
-
-#wbSearch {float:left;padding:30px 30px 0;}
-#wbSearch #logo {float:left; width:223px;}
-#wbSearch #form {float:left;width:707px;}
-#wbSearch form {margin:0;padding:0;}
-#wbSearch input {font-family:"Arial","Helvetica Neue","Helvetica",sans-serif;font-size:1.125em;}
-#wbSearch input[type=text] {width:450px;font-weight:700;}
-#wbSearch input[type=submit] {vertical-align: middle;}
-#wbMeta {padding:15px 0;}
-#wbMeta p {margin:0 0 2px;padding:0;}
-#wbMeta p.wbThis {font-size:0.75em;}
-#wbMeta p.wbNote {color:#666;font-size: 0.6875em;}
-#wbMeta p.wbNote a {color:#666;}
-#wbChart {text-align:center;padding:0 30px;}
-#wbChartThis {position:relative;margin:0 auto;}
-.wbChartThisContainer,.wbChartHover {width:<%= yearWidth %>px;height:30px;float:left;overflow:visible;}
-.wbChartThisTop {
- width: <%= yearWidth %>px;
- height: 80px;
- border: 1px solid #ccc;
-}
-.wbGradient {
- background: #f3f3f3 -moz-linear-gradient(top,#ffffff,#f3f3f3);
- background: #f3f3f3 -webkit-gradient(linear, left top, left bottom, from(#fff), to(#f3f3f3), color-stop(1.0, #f3f3f3));
- background-color: #f3f3f3;
- filter: progid:DXImageTransform.Microsoft.Gradient(enabled='true',startColorstr=#FFFFFFFF, endColorstr=#FFF3F3F3);
-}
-.wbSelected, #wbSelected {
- background: #fff300!important;
- border-bottom: 1px solid #000!important;
- filter: progid:DXImageTransform.Microsoft.Gradient(enabled='false')!important;
- cursor: pointer;
-}
-#wbSelected {
- cursor: default!important;
-}
-.wbChartThisBtm {
- text-align:center;
-}
-.wbChartSm {
- padding-top: 4px;
- font-size: 0.625em;
- color: #999;
- font-weight: 700;
-}
-.wbChartBig, #wbChartBig {
- background-color: #000!important;
- padding-top: 4px;
- font-size: 1.375em!important;
- color: #fff300!important;
- font-weight: normal!important;
- cursor: pointer;
-}
-#wbChartBig {
- cursor: default!important;
-}
-#wbChartGraph,#wbChartOver {
- position: absolute;
- top: 1px;
- left: 1px;
- cursor: pointer;
-}
-
-</style>
-
-<script type="text/javascript">
$().ready(function(){
var yrCount = $(".wbChartThisContainer").size();
var yrTotal = <%= yearWidth %> * yrCount;
@@ -366,14 +200,41 @@
});
</script>
-<div id="wbChart">
+<div id="position">
+
+
+ <div id="wbSearch">
+ <div id="logo">
+ <a href="/index.jsp"><img src="<%= staticPrefix %>images/logo_WM.png" alt="logo: Internet Archive's Wayback Machine" width="183" height="65" /></a>
+ </div>
+
+ <div id="form">
+
+ <form name="form1" method="get" action="<%= queryPrefix %>query">
+ <input type="hidden" name="<%= WaybackRequest.REQUEST_TYPE %>" value="<%= WaybackRequest.REQUEST_CAPTURE_QUERY %>">
+ <input type="text" name="<%= WaybackRequest.REQUEST_URL %>" value="<%= data.searchUrlForHTML %>" size="40">
+ <input type="submit" name="Submit" value="Go Wayback!"/>
+ </form>
+
+ <div id="wbMeta">
+ <p class="wbThis"><a href="<%= data.searchUrlForHTML %>"><%= data.searchUrlForHTML %></a> has been crawled <strong><%= fmt.format("{0} times",data.numResults) %></strong> going all the way back to <a href="firstcapture"><%= fmt.format("{0,date,MMM dd yyyy}",data.firstResultDate) %></a>.</p>
+ <p class="wbNote">A crawl can be a duplicate of the last one. It happens about [num]% of the time across [NUM] websites. <a href="FAQ">FAQ</a></p>
+ </div>
+ </div>
+
+ </div>
+
+ <div class="clearfix"></div>
+
+ <div id="wbChart" onmouseout="showTrackers('none'); setActiveYear(startYear);">
+
<div id="wbChartThis">
<a style="position:relative; white-space:nowrap; width:<%= imgWidth %>px;height:<%= imgHeight %>px;" href="" id="wm-graph-anchor">
<div id="wm-ipp-sparkline" style="position:relative; white-space:nowrap; width:<%= imgWidth %>px;height:<%= imgHeight %>px;background: #f3f3f3 -moz-linear-gradient(top,#ffffff,#f3f3f3);background: #f3f3f3 -webkit-gradient(linear, left top, left bottom, from(#fff), to(#f3f3f3), color-stop(1.0, #f3f3f3));background-color: #f3f3f3;filter: progid:DXImageTransform.Microsoft.Gradient(enabled='true',startColorstr=#FFFFFFFF, endColorstr=#FFF3F3F3);cursor:pointer;border: 1px solid #ccc;border-left:none;" title="<%= fmt.format("ToolBar.sparklineTitle") %>">
<img id="sparklineImgId" style="position:absolute;z-index:9012;top:0;left:0;"
onmouseover="showTrackers('inline');"
- onmouseout="showTrackers('none');"
+
onmousemove="trackMouseMove(event,this)"
alt="sparklines"
width="<%= imgWidth %>"
@@ -385,13 +246,13 @@
width="<%= yearWidth %>"
height="<%= imgHeight %>"
border="0"
- src="<%= staticPrefix %>images/toolbar/transp-yellow-pixel.png"></img>
+ src="<%= staticPrefix %>images/toolbar/yellow-pixel.png"></img>
<img id="wbMouseTrackMonthImg"
style="display:none; position:absolute; z-index:9011; "
width="<%= monthWidth %>"
height="<%= imgHeight %>"
border="0"
- src="<%= staticPrefix %>images/toolbar/transp-red-pixel.png"></img>
+ src="<%= staticPrefix %>images/toolbar/transp-black-pixel.png"></img>
</div>
</a>
<%
@@ -406,7 +267,6 @@
<div id="highlight-<%= i - 1996 %>"
onmouseover="showTrackers('inline'); setActiveYear(<%= i - 1996 %>)"
- onmouseout="showTrackers('none');"
class="<%= curClass %>"><%= i %></div>
</a>
</div>
@@ -461,12 +321,13 @@
String replayUrl = uriConverter.makeReplayURI(
firstCaptureInDay.getCaptureTimestamp(),
firstCaptureInDay.getOriginalUrl());
+ Date firstCaptureInDayDate = firstCaptureInDay.getCaptureDate();
String safeUrl = fmt.escapeHtml(replayUrl);
%><td>
<div class="date">
<div class="position">
<div class="hidden"><%= count %></div>
- <div class="measure opacity20" id=""><img width="100%" height="100%"/></div>
+ <div class="measure opacity20" id="<%= fmt.format("{0,date,MMM-d-yyyy}",firstCaptureInDayDate) %>"><img width="100%" height="100%"/></div>
</div>
</div>
</td><%
@@ -541,13 +402,12 @@
firstCaptureInDay.getOriginalUrl());
Date firstCaptureInDayDate = firstCaptureInDay.getCaptureDate();
String safeUrl = fmt.escapeHtml(replayUrl);
- int dupes = 999;
%><td>
<div class="date tooltip">
<div class="pop">
<h3><%= fmt.format("{0,date,MMMMM d, yyyy}",firstCaptureInDayDate) %></h3>
- <p><%= count %> snapshots, <em><%= dupes %> duplicates</em></p>
+ <p><%= count %> snapshots</p>
<ul>
<%
Iterator<CaptureSearchResult> dayItr =
@@ -566,7 +426,7 @@
</div>
<div class="day">
- <a href="<%= safeUrl %>" title="<%= count %> snapshots (<%= dupes %> duplicates)" class="<%= fmt.format("{0,date,MMM-d-yyyy}",firstCaptureInDayDate) %>"><%= dom + 1 %></a>
+ <a href="<%= safeUrl %>" title="<%= count %> snapshots" class="<%= fmt.format("{0,date,MMM-d-yyyy}",firstCaptureInDayDate) %>"><%= dom + 1 %></a>
</div>
</div>
</td><%
@@ -601,4 +461,4 @@
}
%>
</div>
- </div>
\ No newline at end of file
+<jsp:include page="/WEB-INF/global-template/UI-footer.jsp" flush="true" />
\ No newline at end of file
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bi...@us...> - 2010-07-16 20:26:09
|
Revision: 3171
http://archive-access.svn.sourceforge.net/archive-access/?rev=3171&view=rev
Author: binzino
Date: 2010-07-16 20:26:03 +0000 (Fri, 16 Jul 2010)
Log Message:
-----------
Local edits of Nutch file to over-ride chatty log messages.
Added Paths:
-----------
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/parse/
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/parse/ParseUtil.java
Added: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/parse/ParseUtil.java
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/parse/ParseUtil.java (rev 0)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/parse/ParseUtil.java 2010-07-16 20:26:03 UTC (rev 3171)
@@ -0,0 +1,139 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.nutch.parse;
+
+// Commons Logging imports
+import org.apache.commons.logging.Log;
+import org.apache.commons.logging.LogFactory;
+
+// Nutch Imports
+import org.apache.nutch.protocol.Content;
+
+// Hadoop imports
+import org.apache.hadoop.conf.Configuration;
+
+
+/**
+ * A Utility class containing methods to simply perform parsing utilities such
+ * as iterating through a preferred list of {@link Parser}s to obtain
+ * {@link Parse} objects.
+ *
+ * @author mattmann
+ * @author Jérôme Charron
+ * @author Sébastien Le Callonnec
+ */
+public class ParseUtil {
+
+ /* our log stream */
+ public static final Log LOG = LogFactory.getLog(ParseUtil.class);
+ private ParserFactory parserFactory;
+
+ /**
+ *
+ * @param conf
+ */
+ public ParseUtil(Configuration conf) {
+ this.parserFactory = new ParserFactory(conf);
+ }
+
+ /**
+ * Performs a parse by iterating through a List of preferred {@link Parser}s
+ * until a successful parse is performed and a {@link Parse} object is
+ * returned. If the parse is unsuccessful, a message is logged to the
+ * <code>WARNING</code> level, and an empty parse is returned.
+ *
+ * @param content The content to try and parse.
+ * @return <key, {@link Parse}> pairs.
+ * @throws ParseException If no suitable parser is found to perform the parse.
+ */
+ public ParseResult parse(Content content) throws ParseException {
+ Parser[] parsers = null;
+
+ try {
+ parsers = this.parserFactory.getParsers(content.getContentType(),
+ content.getUrl() != null ? content.getUrl():"");
+ } catch (ParserNotFound e) {
+ if (LOG.isDebugEnabled()) {
+ LOG.debug("No suitable parser found when trying to parse content " + content.getUrl() +
+ " of type " + content.getContentType());
+ }
+ throw new ParseException(e.getMessage());
+ }
+
+ ParseResult parseResult = null;
+ for (int i=0; i<parsers.length; i++) {
+ if (LOG.isDebugEnabled()) {
+ LOG.debug("Parsing [" + content.getUrl() + "] with [" + parsers[i] + "]");
+ }
+ parseResult = parsers[i].getParse(content);
+ if (parseResult != null && !parseResult.isEmpty())
+ return parseResult;
+ }
+
+ if (LOG.isDebugEnabled()) {
+ LOG.debug("Unable to successfully parse content " + content.getUrl() +
+ " of type " + content.getContentType());
+ }
+ return null;
+ }
+
+ /**
+ * Method parses a {@link Content} object using the {@link Parser} specified
+ * by the parameter <code>extId</code>, i.e., the Parser's extension ID.
+ * If a suitable {@link Parser} is not found, then a <code>WARNING</code>
+ * level message is logged, and a ParseException is thrown. If the parse is
+ * uncessful for any other reason, then a <code>WARNING</code> level
+ * message is logged, and a <code>ParseStatus.getEmptyParse()</code> is
+ * returned.
+ *
+ * @param extId The extension implementation ID of the {@link Parser} to use
+ * to parse the specified content.
+ * @param content The content to parse.
+ *
+ * @return <key, {@link Parse}> pairs if the parse is successful, otherwise,
+ * a single <key, <code>ParseStatus.getEmptyParse()</code>> pair.
+ *
+ * @throws ParseException If there is no suitable {@link Parser} found
+ * to perform the parse.
+ */
+ public ParseResult parseByExtensionId(String extId, Content content)
+ throws ParseException {
+ Parser p = null;
+
+ try {
+ p = this.parserFactory.getParserById(extId);
+ } catch (ParserNotFound e) {
+ if (LOG.isDebugEnabled()) {
+ LOG.debug("No suitable parser found when trying to parse content " + content.getUrl() +
+ " of type " + content.getContentType());
+ }
+ throw new ParseException(e.getMessage());
+ }
+
+ ParseResult parseResult = p.getParse(content);
+ if (parseResult != null && !parseResult.isEmpty()) {
+ return parseResult;
+ } else {
+ if (LOG.isDebugEnabled()) {
+ LOG.debug("Unable to successfully parse content " + content.getUrl() +
+ " of type " + content.getContentType());
+ }
+ return null;
+ }
+ }
+
+}
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bi...@us...> - 2010-07-16 20:25:47
|
Revision: 3170
http://archive-access.svn.sourceforge.net/archive-access/?rev=3170&view=rev
Author: binzino
Date: 2010-07-16 20:25:38 +0000 (Fri, 16 Jul 2010)
Log Message:
-----------
Changed logging levels to be less chatty.
Modified Paths:
--------------
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/Importer.java
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/urlfilter-nutchwax/src/java/org/archive/nutchwax/urlfilter/WaybackURLFilter.java
Modified: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/Importer.java
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/Importer.java 2010-07-12 02:26:34 UTC (rev 3169)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/Importer.java 2010-07-16 20:25:38 UTC (rev 3170)
@@ -193,13 +193,14 @@
if ( LOG.isInfoEnabled() ) LOG.info( "Importing ARC: " + arcUrl );
- ArchiveReader r = ArchiveReaderFactory.get( arcUrl );
- r.setDigest( true );
-
- ArcReader reader = new ArcReader( r );
-
+ ArchiveReader r = null;
try
{
+ r = ArchiveReaderFactory.get( arcUrl );
+ r.setDigest( true );
+
+ ArcReader reader = new ArcReader( r );
+
for ( ARCRecord record : reader )
{
// When reading WARC files, records of type other than
@@ -214,7 +215,7 @@
}
catch ( Exception e )
{
- LOG.warn( "Error processing archive file: " + arcUrl, e );
+ LOG.error( "Error processing archive file: " + arcUrl, e );
if ( jobConf.getBoolean( "nutchwax.import.abortOnArchiveReadError", false ) )
{
@@ -223,7 +224,7 @@
}
finally
{
- r.close();
+ if ( r != null ) r.close();
if ( LOG.isInfoEnabled() )
{
@@ -246,11 +247,11 @@
{
ARCRecordMetaData meta = record.getMetaData();
- if ( LOG.isInfoEnabled() ) LOG.info( "Consider URL: " + meta.getUrl() + " (" + meta.getMimetype() + ") [" + meta.getLength( ) + "]" );
+ if ( LOG.isDebugEnabled() ) LOG.debug( "Consider URL: " + meta.getUrl() + " (" + meta.getMimetype() + ") [" + meta.getLength( ) + "]" );
if ( ! this.httpStatusCodeFilter.isAllowed( record.getStatusCode( ) ) )
{
- if ( LOG.isInfoEnabled() ) LOG.info( "Skip URL: " + meta.getUrl() + " HTTP status:" + record.getStatusCode() );
+ if ( LOG.isDebugEnabled() ) LOG.debug( "Skip URL: " + meta.getUrl() + " HTTP status:" + record.getStatusCode() );
return false;
}
@@ -291,7 +292,7 @@
if ( url == null )
{
- if ( LOG.isInfoEnabled() ) LOG.info( "Skip URL: " + meta.getUrl() );
+ if ( LOG.isDebugEnabled() ) LOG.debug( "Skip URL: " + meta.getUrl() );
return false;
}
@@ -375,11 +376,11 @@
}
catch ( MalformedURLException mue )
{
- if ( LOG.isInfoEnabled() ) LOG.info( "MalformedURL: " + candidateUrl );
+ if ( LOG.isDebugEnabled() ) LOG.debug( "MalformedURL: " + candidateUrl );
}
catch ( URLFilterException ufe )
{
- if ( LOG.isInfoEnabled() ) LOG.info( "URL filtered: " + candidateUrl );
+ if ( LOG.isDebugEnabled() ) LOG.debug( "URL filtered: " + candidateUrl );
}
return null;
@@ -439,9 +440,9 @@
{
parseResult = this.parseUtil.parse( content );
}
- catch ( Exception e )
+ catch ( Throwable t )
{
- LOG.warn( "Error parsing: " + key, e );
+ if ( LOG.isDebugEnabled() ) LOG.debug( "Error parsing: " + key, t );
}
// ?: This is taken from Nutch Fetcher. I believe the signatures are used in the Fetcher
@@ -590,7 +591,7 @@
count += record.read( buf, 0, Math.min( buf.length, record.available( ) ) );
}
- if ( LOG.isInfoEnabled() ) LOG.info( "Bytes read: expected=" + contentLength + " bytes.length=" + bytes.length + " pos=" + pos + " count=" + count );
+ if ( LOG.isDebugEnabled() ) LOG.debug( "Bytes read: expected=" + contentLength + " bytes.length=" + bytes.length + " pos=" + pos + " count=" + count );
// Sanity check. The number of bytes read into our bytes[]
// buffer, plus the count of extra stuff read after it should
Modified: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/urlfilter-nutchwax/src/java/org/archive/nutchwax/urlfilter/WaybackURLFilter.java
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/urlfilter-nutchwax/src/java/org/archive/nutchwax/urlfilter/WaybackURLFilter.java 2010-07-12 02:26:34 UTC (rev 3169)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/urlfilter-nutchwax/src/java/org/archive/nutchwax/urlfilter/WaybackURLFilter.java 2010-07-16 20:25:38 UTC (rev 3170)
@@ -70,7 +70,7 @@
if ( s.length != 3 )
{
// Don't filter.
- LOG.info( "Allowing : " + urlString );
+ if ( LOG.isDebugEnabled() ) LOG.debug( "Allowing : " + urlString );
return urlString;
}
@@ -101,12 +101,12 @@
if ( exclude )
{
- LOG.info( "Excluding: " + urlString );
+ if ( LOG.isDebugEnabled() ) LOG.debug( "Excluding: " + urlString );
return null;
}
- LOG.info( "Allowing : " + urlString );
+ if ( LOG.isDebugEnabled() ) LOG.debug( "Allowing : " + urlString );
return urlString;
}
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bi...@us...> - 2010-07-12 02:26:43
|
Revision: 3169
http://archive-access.svn.sourceforge.net/archive-access/?rev=3169&view=rev
Author: binzino
Date: 2010-07-12 02:26:34 +0000 (Mon, 12 Jul 2010)
Log Message:
-----------
Remove setting of segment and digest fields.
Modified Paths:
--------------
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/IndexerMapReduce.java
Modified: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/IndexerMapReduce.java
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/IndexerMapReduce.java 2010-07-11 00:09:27 UTC (rev 3168)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/IndexerMapReduce.java 2010-07-12 02:26:34 UTC (rev 3169)
@@ -96,10 +96,10 @@
}
// add segment, used to map from merged index back to segment files
- doc.add("segment", metadata.get(Nutch.SEGMENT_NAME_KEY));
+ //doc.add("segment", metadata.get(Nutch.SEGMENT_NAME_KEY));
// add digest, used by dedup
- doc.add("digest", metadata.get(Nutch.SIGNATURE_KEY));
+ //doc.add("digest", metadata.get(Nutch.SIGNATURE_KEY));
final Parse parse = new ParseImpl(parseText, parseData);
try {
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bi...@us...> - 2010-07-11 00:09:35
|
Revision: 3168
http://archive-access.svn.sourceforge.net/archive-access/?rev=3168&view=rev
Author: binzino
Date: 2010-07-11 00:09:27 +0000 (Sun, 11 Jul 2010)
Log Message:
-----------
A whole mess of accumulated hacks to get Importing and Indexing working with Hadoop 0.20 (Cloudera) on our Hadoop rack.
Modified Paths:
--------------
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/IndexMerger.java
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/Indexer.java
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/tools/BuildIndex.java
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/tools/DateAdder.java
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/tools/DumpParallelIndex.java
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/tools/GetUniqFieldValues.java
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/tools/LengthNormUpdater.java
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/conf/nutch-site.xml
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/lucene/index/ArchiveParallelReader.java
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/plugin/query-nutchwax/src/java/org/archive/nutchwax/query/DateQueryFilter.java
Added Paths:
-----------
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/conf/common-terms.utf8
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/indexer/
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/indexer/lucene/
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/indexer/lucene/LuceneWriter.java
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/plugin/
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/plugin/PluginManifestParser.java
Removed Paths:
-------------
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/searcher/DistributedSearch.java
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/searcher/DistributedSegmentBean.java
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/searcher/FetchedSegments.java
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/searcher/IndexSearcher.java
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/searcher/LuceneSearchBean.java
tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/searcher/NutchBean.java
Modified: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/IndexMerger.java
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/IndexMerger.java 2010-07-10 23:34:25 UTC (rev 3167)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/IndexMerger.java 2010-07-11 00:09:27 UTC (rev 3168)
@@ -34,9 +34,10 @@
import org.apache.nutch.indexer.NutchSimilarity;
import org.apache.nutch.indexer.FsDirectory;
-import org.apache.lucene.store.Directory;
+import org.apache.lucene.store.NIOFSDirectory;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexReader;
+import org.apache.lucene.index.LogMergePolicy;
import org.apache.lucene.index.ArchiveParallelReader;
/*************************************************************************
@@ -84,10 +85,10 @@
//
// Merge indices
//
- IndexWriter writer = new IndexWriter(localOutput.toString(), null, true);
- writer.setMergeFactor(getConf().getInt("indexer.mergeFactor", IndexWriter.DEFAULT_MERGE_FACTOR));
+ IndexWriter writer = new IndexWriter( new NIOFSDirectory( new File( localOutput.toString() ) ), null, IndexWriter.MaxFieldLength.UNLIMITED );
+ writer.setMergeFactor(getConf().getInt("indexer.mergeFactor", LogMergePolicy.DEFAULT_MERGE_FACTOR));
writer.setMaxBufferedDocs(getConf().getInt("indexer.minMergeDocs", IndexWriter.DEFAULT_MAX_BUFFERED_DOCS));
- writer.setMaxMergeDocs(getConf().getInt("indexer.maxMergeDocs", IndexWriter.DEFAULT_MAX_MERGE_DOCS));
+ writer.setMaxMergeDocs(getConf().getInt("indexer.maxMergeDocs", LogMergePolicy.DEFAULT_MAX_MERGE_DOCS));
writer.setTermIndexInterval(getConf().getInt("indexer.termIndexInterval", IndexWriter.DEFAULT_TERM_INDEX_INTERVAL));
writer.setInfoStream(LogUtil.getDebugStream(LOG));
writer.setUseCompoundFile(false);
Modified: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/Indexer.java
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/Indexer.java 2010-07-10 23:34:25 UTC (rev 3167)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/Indexer.java 2010-07-11 00:09:27 UTC (rev 3168)
@@ -63,8 +63,8 @@
FileOutputFormat.setOutputPath(job, luceneDir);
- LuceneWriter.addFieldOptions("segment", LuceneWriter.STORE.YES, LuceneWriter.INDEX.NO, job);
- LuceneWriter.addFieldOptions("digest", LuceneWriter.STORE.YES, LuceneWriter.INDEX.NO, job);
+ //LuceneWriter.addFieldOptions("segment", LuceneWriter.STORE.YES, LuceneWriter.INDEX.NO, job);
+ //LuceneWriter.addFieldOptions("digest", LuceneWriter.STORE.YES, LuceneWriter.INDEX.NO, job);
NutchIndexWriterFactory.addClassToConf(job, LuceneWriter.class);
Modified: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/tools/BuildIndex.java
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/tools/BuildIndex.java 2010-07-10 23:34:25 UTC (rev 3167)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/tools/BuildIndex.java 2010-07-11 00:09:27 UTC (rev 3168)
@@ -20,13 +20,16 @@
*/
package org.archive.nutchwax.tools;
-import org.apache.lucene.index.IndexWriter;
-import org.apache.lucene.document.Document;
-import org.apache.lucene.document.Field;
-import org.apache.lucene.analysis.WhitespaceAnalyzer;
+import java.io.*;
+
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
+import org.apache.lucene.analysis.WhitespaceAnalyzer;
+import org.apache.lucene.document.Document;
+import org.apache.lucene.document.Field;
+import org.apache.lucene.index.IndexWriter;
+import org.apache.lucene.store.NIOFSDirectory;
import org.apache.nutch.util.NutchConfiguration;
@@ -50,12 +53,12 @@
String fieldValue = args[2].trim();
int count = Integer.parseInt( args[3].trim() );
- IndexWriter writer = new IndexWriter( indexDir, new WhitespaceAnalyzer( ), true );
+ IndexWriter writer = new IndexWriter( new NIOFSDirectory( new File( indexDir ) ), null, IndexWriter.MaxFieldLength.UNLIMITED );
for ( int i = 0 ; i < count ; i++ )
{
Document newDoc = new Document( );
- newDoc.add( new Field( fieldKey, fieldValue, Field.Store.YES, Field.Index.TOKENIZED ) );
+ newDoc.add( new Field( fieldKey, fieldValue, Field.Store.YES, Field.Index.ANALYZED ) );
writer.addDocument( newDoc );
}
Modified: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/tools/DateAdder.java
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/tools/DateAdder.java 2010-07-10 23:34:25 UTC (rev 3167)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/tools/DateAdder.java 2010-07-11 00:09:27 UTC (rev 3168)
@@ -20,21 +20,15 @@
*/
package org.archive.nutchwax.tools;
-import java.io.BufferedReader;
-import java.io.FileInputStream;
-import java.io.InputStream;
-import java.io.InputStreamReader;
-import java.util.Collections;
-import java.util.HashMap;
-import java.util.HashSet;
-import java.util.Map;
-import java.util.Set;
+import java.io.*;
+import java.util.*;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.analysis.WhitespaceAnalyzer;
+import org.apache.lucene.store.NIOFSDirectory;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.conf.Configuration;
@@ -104,15 +98,15 @@
}
- IndexReader reader = IndexReader.open( mainIndexDir );
+ IndexReader reader = IndexReader.open( new NIOFSDirectory( new File( mainIndexDir ) ), true );
IndexReader sourceReaders[] = new IndexReader[args.length-3];
for ( int i = 0 ; i < sourceReaders.length ; i++ )
{
- sourceReaders[i] = IndexReader.open( args[i+1] );
+ sourceReaders[i] = IndexReader.open( new NIOFSDirectory( new File( args[i+1] ) ), true );
}
- IndexWriter writer = new IndexWriter( destIndexDir, new WhitespaceAnalyzer( ), true );
+ IndexWriter writer = new IndexWriter( new NIOFSDirectory( new File( destIndexDir ) ), null, IndexWriter.MaxFieldLength.UNLIMITED );
UrlCanonicalizer canonicalizer = getCanonicalizer( this.getConf( ) );
@@ -134,7 +128,7 @@
}
for ( String date : uniqueDates )
{
- newDoc.add( new Field( NutchWax.DATE_KEY, date, Field.Store.YES, Field.Index.UN_TOKENIZED ) );
+ newDoc.add( new Field( NutchWax.DATE_KEY, date, Field.Store.YES, Field.Index.NOT_ANALYZED ) );
}
// Obtain the new dates for the document.
@@ -162,7 +156,7 @@
{
for ( String date : newDates.split("\\s+") )
{
- newDoc.add( new Field( NutchWax.DATE_KEY, date, Field.Store.YES, Field.Index.UN_TOKENIZED ) );
+ newDoc.add( new Field( NutchWax.DATE_KEY, date, Field.Store.YES, Field.Index.NOT_ANALYZED ) );
}
}
Modified: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/tools/DumpParallelIndex.java
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/tools/DumpParallelIndex.java 2010-07-10 23:34:25 UTC (rev 3167)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/tools/DumpParallelIndex.java 2010-07-11 00:09:27 UTC (rev 3168)
@@ -27,7 +27,9 @@
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.ArchiveParallelReader;
+import org.apache.lucene.store.NIOFSDirectory;
+
public class DumpParallelIndex
{
public static void main( String[] args ) throws Exception
@@ -58,7 +60,7 @@
ArchiveParallelReader reader = new ArchiveParallelReader( );
for ( String dir : dirs )
{
- reader.add( IndexReader.open( dir ) );
+ reader.add( IndexReader.open( new NIOFSDirectory( new File( dir ) ) ) );
}
if ( args[0].equals( "-l" ) )
Modified: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/tools/GetUniqFieldValues.java
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/tools/GetUniqFieldValues.java 2010-07-10 23:34:25 UTC (rev 3167)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/tools/GetUniqFieldValues.java 2010-07-11 00:09:27 UTC (rev 3168)
@@ -20,13 +20,11 @@
*/
package org.archive.nutchwax.tools;
-import java.io.File;
-import java.util.Iterator;
-import java.util.Set;
-import java.util.HashSet;
-import java.util.Collection;
+import java.io.*;
+import java.util.*;
import org.apache.lucene.index.IndexReader;
+import org.apache.lucene.store.NIOFSDirectory;
/**
* A quick-n-dirty command-line utility to get the unique values for a
@@ -55,7 +53,7 @@
private static void dumpUniqValues( String fieldName, String indexDir ) throws Exception
{
- IndexReader reader = IndexReader.open(indexDir);
+ IndexReader reader = IndexReader.open( new NIOFSDirectory( new File( indexDir) ) );
Collection fieldNames = reader.getFieldNames( IndexReader.FieldOption.ALL );
Modified: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/tools/LengthNormUpdater.java
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/tools/LengthNormUpdater.java 2010-07-10 23:34:25 UTC (rev 3167)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/java/org/archive/nutchwax/tools/LengthNormUpdater.java 2010-07-11 00:09:27 UTC (rev 3168)
@@ -16,15 +16,8 @@
* limitations under the License.
*/
-import java.io.BufferedReader;
-import java.io.InputStreamReader;
-import java.io.FileInputStream;
-import java.io.IOException;
-import java.util.HashMap;
-import java.util.Map;
-import java.util.Set;
-import java.util.Collection;
-import java.util.HashSet;
+import java.io.*;
+import java.util.*;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.Term;
@@ -32,12 +25,11 @@
import org.apache.lucene.index.TermDocs;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.search.Similarity;
-import org.apache.lucene.store.Directory;
-import org.apache.lucene.store.FSDirectory;
+import org.apache.lucene.store.NIOFSDirectory;
-
import org.apache.nutch.indexer.NutchSimilarity;
+
/**
* This is heavily cribbed from org.apache.lucene.misc.LengthNormModifier
*/
@@ -132,7 +124,7 @@
String pagerankFile = args[pos++];
- IndexReader reader = IndexReader.open( args[pos++] );
+ IndexReader reader = IndexReader.open( new NIOFSDirectory( new File( args[pos++] ) ) );
try
{
Added: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/conf/common-terms.utf8
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/conf/common-terms.utf8 (rev 0)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/conf/common-terms.utf8 2010-07-11 00:09:27 UTC (rev 3168)
@@ -0,0 +1,28 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# Common terms and phrases which will be indexed in n-grams
+# in order to optimize search.
+#content:a
+#content:and
+#content:for
+#content:in
+#content:of
+#content:the
+#content:to
+#url:com
+#url:http
+#url:http-www
+#url:www
Modified: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/conf/nutch-site.xml
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/conf/nutch-site.xml 2010-07-10 23:34:25 UTC (rev 3167)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/conf/nutch-site.xml 2010-07-11 00:09:27 UTC (rev 3168)
@@ -10,7 +10,7 @@
<!-- Add 'index-nutchwax' and 'query-nutchwax' to plugin list. -->
<!-- Also, add 'parse-pdf' -->
<!-- Remove 'urlfilter-regex' and 'normalizer-(pass|regex|basic)' -->
- <value>protocol-http|parse-(text|html|js|pdf)|index-nutchwax|query-(basic|nutchwax)|summary-basic|scoring-nutchwax|urlfilter-nutchwax</value>
+ <value>protocol-http|parse-(text|html|pdf|msword|mspowerpoint|oo)|index-nutchwax|query-(basic|nutchwax)|summary-basic|scoring-nutchwax|urlfilter-nutchwax</value>
</property>
<!--
@@ -42,6 +42,7 @@
dest-key = src-key
-->
<name>nutchwax.filter.index</name>
+<!--
<value>
title:false:true:tokenized
content:false:compress:tokenized
@@ -55,6 +56,16 @@
type:true:true:no_norms
length:false:true:no
</value>
+-->
+ <value>
+ title:false:true:tokenized
+ content:false:compress:tokenized
+ site:false:false:untokenized
+ url:false:true:tokenized
+ type:true:true:no_norms
+ date:false:true:no
+ length:false:true:no
+ </value>
</property>
<property>
Modified: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/lucene/index/ArchiveParallelReader.java
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/lucene/index/ArchiveParallelReader.java 2010-07-10 23:34:25 UTC (rev 3167)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/lucene/index/ArchiveParallelReader.java 2010-07-11 00:09:27 UTC (rev 3168)
@@ -1,3 +1,5 @@
+package org.apache.lucene.index;
+
/**
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
@@ -14,24 +16,11 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
-/**
- * ARCHIVE: This must be in the lucene index package because it needs
- * to call protected methods on other IndexReader objects.
- */
-package org.apache.lucene.index;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.FieldSelector;
import org.apache.lucene.document.FieldSelectorResult;
import org.apache.lucene.document.Fieldable;
-import org.apache.lucene.index.CorruptIndexException;
-import org.apache.lucene.index.IndexReader;
-import org.apache.lucene.index.Term;
-import org.apache.lucene.index.TermDocs;
-import org.apache.lucene.index.TermEnum;
-import org.apache.lucene.index.TermFreqVector;
-import org.apache.lucene.index.TermPositions;
-import org.apache.lucene.index.TermVectorMapper;
import java.io.IOException;
import java.util.*;
@@ -55,10 +44,12 @@
* undefined behavior</em>.
*/
public class ArchiveParallelReader extends IndexReader {
- private List readers = new ArrayList();
- private List decrefOnClose = new ArrayList(); // remember which subreaders to decRef on close
+ private List<IndexReader> readers = new ArrayList<IndexReader>();
+ private List<Boolean> decrefOnClose = new ArrayList<Boolean>(); // remember which subreaders to decRef on close
boolean incRefReaders = false;
- private SortedMap fieldToReader = new TreeMap();
+ private SortedMap<String,IndexReader> fieldToReader = new TreeMap<String,IndexReader>();
+ private Map<IndexReader,Collection<String>> readerToFields = new HashMap<IndexReader,Collection<String>>();
+ private List<IndexReader> storedFieldReaders = new ArrayList<IndexReader>();
private int maxDoc;
private int numDocs;
@@ -81,9 +72,25 @@
/** Add an IndexReader.
* @throws IOException if there is a low-level IO error
*/
- public void add(IndexReader reader) throws IOException
- {
+ public void add(IndexReader reader) throws IOException {
ensureOpen();
+ add(reader, false);
+ }
+
+ /** Add an IndexReader whose stored fields will not be returned. This can
+ * accelerate search when stored fields are only needed from a subset of
+ * the IndexReaders.
+ *
+ * @throws IllegalArgumentException if not all indexes contain the same number
+ * of documents
+ * @throws IllegalArgumentException if not all indexes have the same value
+ * of {@link IndexReader#maxDoc()}
+ * @throws IOException if there is a low-level IO error
+ */
+ public void add(IndexReader reader, boolean ignoreStoredFields)
+ throws IOException {
+
+ ensureOpen();
if (readers.size() == 0) {
this.maxDoc = reader.maxDoc();
this.numDocs = reader.numDocs();
@@ -97,14 +104,15 @@
throw new IllegalArgumentException
("All readers must have same numDocs: "+numDocs+"!="+reader.numDocs());
- Collection fields = reader.getFieldNames(IndexReader.FieldOption.ALL);
- Iterator i = fields.iterator();
- while (i.hasNext()) { // update fieldToReader map
- String field = (String)i.next();
+ Collection<String> fields = reader.getFieldNames(IndexReader.FieldOption.ALL);
+ readerToFields.put(reader, fields);
+ for (final String field : fields) { // update fieldToReader map
if (fieldToReader.get(field) == null)
fieldToReader.put(field, reader);
}
+ if (!ignoreStoredFields)
+ storedFieldReaders.add(reader); // add to storedFieldReaders
readers.add(reader);
if (incRefReaders) {
@@ -112,7 +120,16 @@
}
decrefOnClose.add(Boolean.valueOf(incRefReaders));
}
-
+
+ @Override
+ public synchronized Object clone() {
+ try {
+ return doReopen(true);
+ } catch (Exception ex) {
+ throw new RuntimeException(ex);
+ }
+ }
+
/**
* Tries to reopen the subreaders.
* <br>
@@ -132,63 +149,42 @@
* @throws CorruptIndexException if the index is corrupt
* @throws IOException if there is a low-level IO error
*/
- public IndexReader reopen() throws CorruptIndexException, IOException {
+ @Override
+ public synchronized IndexReader reopen() throws CorruptIndexException, IOException {
+ return doReopen(false);
+ }
+
+ protected IndexReader doReopen(boolean doClone) throws CorruptIndexException, IOException {
ensureOpen();
boolean reopened = false;
- List newReaders = new ArrayList();
- List newDecrefOnClose = new ArrayList();
+ List<IndexReader> newReaders = new ArrayList<IndexReader>();
boolean success = false;
try {
-
- for (int i = 0; i < readers.size(); i++) {
- IndexReader oldReader = (IndexReader) readers.get(i);
- IndexReader newReader = oldReader.reopen();
+ for (final IndexReader oldReader : readers) {
+ IndexReader newReader = null;
+ if (doClone) {
+ newReader = (IndexReader) oldReader.clone();
+ } else {
+ newReader = oldReader.reopen();
+ }
newReaders.add(newReader);
// if at least one of the subreaders was updated we remember that
- // and return a new MultiReader
+ // and return a new ArchiveParallelReader
if (newReader != oldReader) {
reopened = true;
}
}
-
- if (reopened) {
- ArchiveParallelReader pr = new ArchiveParallelReader();
- for (int i = 0; i < readers.size(); i++) {
- IndexReader oldReader = (IndexReader) readers.get(i);
- IndexReader newReader = (IndexReader) newReaders.get(i);
- if (newReader == oldReader) {
- newDecrefOnClose.add(Boolean.TRUE);
- newReader.incRef();
- } else {
- // this is a new subreader instance, so on close() we don't
- // decRef but close it
- newDecrefOnClose.add(Boolean.FALSE);
- }
- pr.add(newReader);
- }
- pr.decrefOnClose = newDecrefOnClose;
- pr.incRefReaders = incRefReaders;
- success = true;
- return pr;
- } else {
- success = true;
- // No subreader was refreshed
- return this;
- }
+ success = true;
} finally {
if (!success && reopened) {
for (int i = 0; i < newReaders.size(); i++) {
- IndexReader r = (IndexReader) newReaders.get(i);
- if (r != null) {
+ IndexReader r = newReaders.get(i);
+ if (r != readers.get(i)) {
try {
- if (((Boolean) newDecrefOnClose.get(i)).booleanValue()) {
- r.decRef();
- } else {
- r.close();
- }
+ r.close();
} catch (IOException ignore) {
// keep going - we want to clean up as much as possible
}
@@ -196,46 +192,74 @@
}
}
}
+
+ if (reopened) {
+ List<Boolean> newDecrefOnClose = new ArrayList<Boolean>();
+ ArchiveParallelReader pr = new ArchiveParallelReader();
+ for (int i = 0; i < readers.size(); i++) {
+ IndexReader oldReader = readers.get(i);
+ IndexReader newReader = newReaders.get(i);
+ if (newReader == oldReader) {
+ newDecrefOnClose.add(Boolean.TRUE);
+ newReader.incRef();
+ } else {
+ // this is a new subreader instance, so on close() we don't
+ // decRef but close it
+ newDecrefOnClose.add(Boolean.FALSE);
+ }
+ pr.add(newReader, !storedFieldReaders.contains(oldReader));
+ }
+ pr.decrefOnClose = newDecrefOnClose;
+ pr.incRefReaders = incRefReaders;
+ return pr;
+ } else {
+ // No subreader was refreshed
+ return this;
+ }
}
+ @Override
public int numDocs() {
// Don't call ensureOpen() here (it could affect performance)
return numDocs;
}
+ @Override
public int maxDoc() {
// Don't call ensureOpen() here (it could affect performance)
return maxDoc;
}
+ @Override
public boolean hasDeletions() {
// Don't call ensureOpen() here (it could affect performance)
return hasDeletions;
}
// check first reader
+ @Override
public boolean isDeleted(int n) {
// Don't call ensureOpen() here (it could affect performance)
if (readers.size() > 0)
- return ((IndexReader)readers.get(0)).isDeleted(n);
+ return readers.get(0).isDeleted(n);
return false;
}
// delete in all readers
+ @Override
protected void doDelete(int n) throws CorruptIndexException, IOException {
- for (int i = 0; i < readers.size(); i++) {
- ((IndexReader)readers.get(i)).deleteDocument(n);
+ for (final IndexReader reader : readers) {
+ reader.deleteDocument(n);
}
hasDeletions = true;
}
- /**
- * @see org.apache.lucene.index.ParallelReader.doUndeleteAll
- */
+ // undeleteAll in all readers
+ @Override
protected void doUndeleteAll() throws CorruptIndexException, IOException {
- for (int i = 0; i < readers.size(); i++) {
- ((IndexReader)readers.get(i)).undeleteAll();
+ for (final IndexReader reader : readers) {
+ reader.undeleteAll();
}
hasDeletions = false;
}
@@ -289,111 +313,150 @@
return result;
}
+ /*
+ // append fields from storedFieldReaders
+ @Override
+ public Document document(int n, FieldSelector fieldSelector) throws CorruptIndexException, IOException {
+ ensureOpen();
+ Document result = new Document();
+ for (final IndexReader reader: storedFieldReaders) {
+
+ boolean include = (fieldSelector==null);
+ if (!include) {
+ Collection<String> fields = readerToFields.get(reader);
+ for (final String field : fields)
+ if (fieldSelector.accept(field) != FieldSelectorResult.NO_LOAD) {
+ include = true;
+ break;
+ }
+ }
+ if (include) {
+ List<Fieldable> fields = reader.document(n, fieldSelector).getFields();
+ for (Fieldable field : fields) {
+ result.add(field);
+ }
+ }
+ }
+ return result;
+ }
+ */
+
// get all vectors
+ @Override
public TermFreqVector[] getTermFreqVectors(int n) throws IOException {
ensureOpen();
- ArrayList results = new ArrayList();
- Iterator i = fieldToReader.entrySet().iterator();
- while (i.hasNext()) {
- Map.Entry e = (Map.Entry)i.next();
- String field = (String)e.getKey();
- IndexReader reader = (IndexReader)e.getValue();
+ ArrayList<TermFreqVector> results = new ArrayList<TermFreqVector>();
+ for (final Map.Entry<String,IndexReader> e: fieldToReader.entrySet()) {
+
+ String field = e.getKey();
+ IndexReader reader = e.getValue();
TermFreqVector vector = reader.getTermFreqVector(n, field);
if (vector != null)
results.add(vector);
}
- return (TermFreqVector[])
- results.toArray(new TermFreqVector[results.size()]);
+ return results.toArray(new TermFreqVector[results.size()]);
}
+ @Override
public TermFreqVector getTermFreqVector(int n, String field)
throws IOException {
ensureOpen();
- IndexReader reader = ((IndexReader)fieldToReader.get(field));
+ IndexReader reader = fieldToReader.get(field);
return reader==null ? null : reader.getTermFreqVector(n, field);
}
+ @Override
public void getTermFreqVector(int docNumber, String field, TermVectorMapper mapper) throws IOException {
ensureOpen();
- IndexReader reader = ((IndexReader)fieldToReader.get(field));
+ IndexReader reader = fieldToReader.get(field);
if (reader != null) {
reader.getTermFreqVector(docNumber, field, mapper);
}
}
+ @Override
public void getTermFreqVector(int docNumber, TermVectorMapper mapper) throws IOException {
ensureOpen();
- ensureOpen();
- Iterator i = fieldToReader.entrySet().iterator();
- while (i.hasNext()) {
- Map.Entry e = (Map.Entry)i.next();
- String field = (String)e.getKey();
- IndexReader reader = (IndexReader)e.getValue();
+ for (final Map.Entry<String,IndexReader> e : fieldToReader.entrySet()) {
+
+ String field = e.getKey();
+ IndexReader reader = e.getValue();
reader.getTermFreqVector(docNumber, field, mapper);
}
}
+ @Override
public boolean hasNorms(String field) throws IOException {
ensureOpen();
- IndexReader reader = ((IndexReader)fieldToReader.get(field));
+ IndexReader reader = fieldToReader.get(field);
return reader==null ? false : reader.hasNorms(field);
}
+ @Override
public byte[] norms(String field) throws IOException {
ensureOpen();
- IndexReader reader = ((IndexReader)fieldToReader.get(field));
+ IndexReader reader = fieldToReader.get(field);
return reader==null ? null : reader.norms(field);
}
+ @Override
public void norms(String field, byte[] result, int offset)
throws IOException {
ensureOpen();
- IndexReader reader = ((IndexReader)fieldToReader.get(field));
+ IndexReader reader = fieldToReader.get(field);
if (reader!=null)
reader.norms(field, result, offset);
}
+ @Override
protected void doSetNorm(int n, String field, byte value)
throws CorruptIndexException, IOException {
- IndexReader reader = ((IndexReader)fieldToReader.get(field));
+ IndexReader reader = fieldToReader.get(field);
if (reader!=null)
reader.doSetNorm(n, field, value);
}
+ @Override
public TermEnum terms() throws IOException {
ensureOpen();
return new ParallelTermEnum();
}
+ @Override
public TermEnum terms(Term term) throws IOException {
ensureOpen();
return new ParallelTermEnum(term);
}
+ @Override
public int docFreq(Term term) throws IOException {
ensureOpen();
- IndexReader reader = ((IndexReader)fieldToReader.get(term.field()));
+ IndexReader reader = fieldToReader.get(term.field());
return reader==null ? 0 : reader.docFreq(term);
}
+ @Override
public TermDocs termDocs(Term term) throws IOException {
ensureOpen();
return new ParallelTermDocs(term);
}
+ @Override
public TermDocs termDocs() throws IOException {
ensureOpen();
return new ParallelTermDocs();
}
+ @Override
public TermPositions termPositions(Term term) throws IOException {
ensureOpen();
return new ParallelTermPositions(term);
}
+ @Override
public TermPositions termPositions() throws IOException {
ensureOpen();
return new ParallelTermPositions();
@@ -402,9 +465,10 @@
/**
* Checks recursively if all subreaders are up to date.
*/
+ @Override
public boolean isCurrent() throws CorruptIndexException, IOException {
- for (int i = 0; i < readers.size(); i++) {
- if (!((IndexReader)readers.get(i)).isCurrent()) {
+ for (final IndexReader reader : readers) {
+ if (!reader.isCurrent()) {
return false;
}
}
@@ -416,9 +480,10 @@
/**
* Checks recursively if all subindexes are optimized
*/
+ @Override
public boolean isOptimized() {
- for (int i = 0; i < readers.size(); i++) {
- if (!((IndexReader)readers.get(i)).isOptimized()) {
+ for (final IndexReader reader : readers) {
+ if (!reader.isOptimized()) {
return false;
}
}
@@ -431,36 +496,39 @@
/** Not implemented.
* @throws UnsupportedOperationException
*/
+ @Override
public long getVersion() {
throw new UnsupportedOperationException("ArchiveParallelReader does not support this method.");
}
// for testing
IndexReader[] getSubReaders() {
- return (IndexReader[]) readers.toArray(new IndexReader[readers.size()]);
+ return readers.toArray(new IndexReader[readers.size()]);
}
- protected void doCommit() throws IOException {
- for (int i = 0; i < readers.size(); i++)
- ((IndexReader)readers.get(i)).commit();
+ @Override
+ protected void doCommit(Map<String,String> commitUserData) throws IOException {
+ for (final IndexReader reader : readers)
+ reader.commit(commitUserData);
}
+ @Override
protected synchronized void doClose() throws IOException {
for (int i = 0; i < readers.size(); i++) {
- if (((Boolean) decrefOnClose.get(i)).booleanValue()) {
- ((IndexReader)readers.get(i)).decRef();
+ if (decrefOnClose.get(i).booleanValue()) {
+ readers.get(i).decRef();
} else {
- ((IndexReader)readers.get(i)).close();
+ readers.get(i).close();
}
}
}
- public Collection getFieldNames (IndexReader.FieldOption fieldNames) {
+ @Override
+ public Collection<String> getFieldNames (IndexReader.FieldOption fieldNames) {
ensureOpen();
- Set fieldSet = new HashSet();
- for (int i = 0; i < readers.size(); i++) {
- IndexReader reader = ((IndexReader)readers.get(i));
- Collection names = reader.getFieldNames(fieldNames);
+ Set<String> fieldSet = new HashSet<String>();
+ for (final IndexReader reader : readers) {
+ Collection<String> names = reader.getFieldNames(fieldNames);
fieldSet.addAll(names);
}
return fieldSet;
@@ -468,24 +536,28 @@
private class ParallelTermEnum extends TermEnum {
private String field;
- private Iterator fieldIterator;
+ private Iterator<String> fieldIterator;
private TermEnum termEnum;
public ParallelTermEnum() throws IOException {
- if ( fieldToReader.isEmpty( ) ) return ;
-
- field = (String)fieldToReader.firstKey();
+ try {
+ field = fieldToReader.firstKey();
+ } catch(NoSuchElementException e) {
+ // No fields, so keep field == null, termEnum == null
+ return;
+ }
if (field != null)
- termEnum = ((IndexReader)fieldToReader.get(field)).terms();
+ termEnum = fieldToReader.get(field).terms();
}
public ParallelTermEnum(Term term) throws IOException {
field = term.field();
- IndexReader reader = ((IndexReader)fieldToReader.get(field));
+ IndexReader reader = fieldToReader.get(field);
if (reader!=null)
termEnum = reader.terms(term);
}
+ @Override
public boolean next() throws IOException {
if (termEnum==null)
return false;
@@ -502,8 +574,8 @@
fieldIterator.next(); // Skip field to get next one
}
while (fieldIterator.hasNext()) {
- field = (String) fieldIterator.next();
- termEnum = ((IndexReader)fieldToReader.get(field)).terms(new Term(field, ""));
+ field = fieldIterator.next();
+ termEnum = fieldToReader.get(field).terms(new Term(field));
Term term = termEnum.term();
if (term!=null && term.field()==field)
return true;
@@ -514,6 +586,7 @@
return false; // no more fields
}
+ @Override
public Term term() {
if (termEnum==null)
return null;
@@ -521,6 +594,7 @@
return termEnum.term();
}
+ @Override
public int docFreq() {
if (termEnum==null)
return 0;
@@ -528,6 +602,7 @@
return termEnum.docFreq();
}
+ @Override
public void close() throws IOException {
if (termEnum!=null)
termEnum.close();
@@ -540,13 +615,18 @@
protected TermDocs termDocs;
public ParallelTermDocs() {}
- public ParallelTermDocs(Term term) throws IOException { seek(term); }
+ public ParallelTermDocs(Term term) throws IOException {
+ if (term == null)
+ termDocs = readers.isEmpty() ? null : readers.get(0).termDocs(null);
+ else
+ seek(term);
+ }
public int doc() { return termDocs.doc(); }
public int freq() { return termDocs.freq(); }
public void seek(Term term) throws IOException {
- IndexReader reader = ((IndexReader)fieldToReader.get(term.field()));
+ IndexReader reader = fieldToReader.get(term.field());
termDocs = reader!=null ? reader.termDocs(term) : null;
}
@@ -588,8 +668,9 @@
public ParallelTermPositions() {}
public ParallelTermPositions(Term term) throws IOException { seek(term); }
+ @Override
public void seek(Term term) throws IOException {
- IndexReader reader = ((IndexReader)fieldToReader.get(term.field()));
+ IndexReader reader = fieldToReader.get(term.field());
termDocs = reader!=null ? reader.termPositions(term) : null;
}
@@ -614,3 +695,8 @@
}
}
+
+
+
+
+
Added: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/indexer/lucene/LuceneWriter.java
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/indexer/lucene/LuceneWriter.java (rev 0)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/indexer/lucene/LuceneWriter.java 2010-07-11 00:09:27 UTC (rev 3168)
@@ -0,0 +1,330 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.nutch.indexer.lucene;
+
+import java.io.File;
+import java.io.IOException;
+import java.io.ByteArrayOutputStream;
+import java.io.OutputStreamWriter;
+import java.util.zip.GZIPOutputStream;
+import java.util.HashMap;
+import java.util.HashSet;
+import java.util.Iterator;
+import java.util.List;
+import java.util.Map;
+import java.util.Random;
+import java.util.Set;
+import java.util.Map.Entry;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.mapred.FileOutputFormat;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.lucene.document.Document;
+import org.apache.lucene.document.Field;
+import org.apache.lucene.document.CompressionTools;
+import org.apache.lucene.index.IndexWriter;
+import org.apache.lucene.index.IndexWriter.MaxFieldLength;
+import org.apache.lucene.store.FSDirectory;
+import org.apache.nutch.analysis.AnalyzerFactory;
+import org.apache.nutch.analysis.NutchAnalyzer;
+import org.apache.nutch.analysis.NutchDocumentAnalyzer;
+import org.apache.nutch.indexer.Indexer;
+import org.apache.nutch.indexer.NutchDocument;
+import org.apache.nutch.indexer.NutchIndexWriter;
+import org.apache.nutch.indexer.NutchSimilarity;
+import org.apache.nutch.metadata.Metadata;
+import org.apache.nutch.util.LogUtil;
+
+public class LuceneWriter implements NutchIndexWriter {
+
+ public static enum STORE { YES, NO, COMPRESS }
+
+ public static enum INDEX { NO, NO_NORMS, TOKENIZED, UNTOKENIZED }
+
+ public static enum VECTOR { NO, OFFSET, POS, POS_OFFSET, YES }
+
+ private IndexWriter writer;
+
+ private AnalyzerFactory analyzerFactory;
+
+ private Path perm;
+
+ private Path temp;
+
+ private FileSystem fs;
+
+ private final Map<String, Field.Store> fieldStore;
+ private final Set<String> fieldCompress;
+
+ private final Map<String, Field.Index> fieldIndex;
+
+ private final Map<String, Field.TermVector> fieldVector;
+
+ public LuceneWriter() {
+ fieldStore = new HashMap<String, Field.Store>();
+ fieldCompress = new HashSet<String>();
+ fieldIndex = new HashMap<String, Field.Index>();
+ fieldVector = new HashMap<String, Field.TermVector>();
+ }
+
+ private Document createLuceneDoc(NutchDocument doc) {
+ final Document out = new Document();
+
+ out.setBoost(doc.getScore());
+
+ final Metadata documentMeta = doc.getDocumentMeta();
+ for (final Entry<String, List<String>> entry : doc) {
+ final String fieldName = entry.getKey();
+
+ Field.Store store = fieldStore.get(fieldName);
+ boolean compress = fieldCompress.contains(fieldName);
+ Field.Index index = fieldIndex.get(fieldName);
+ Field.TermVector vector = fieldVector.get(fieldName);
+
+ // default values
+ if (store == null) {
+ store = Field.Store.NO;
+ }
+
+ if (index == null) {
+ index = Field.Index.NO;
+ }
+
+ if (vector == null) {
+ vector = Field.TermVector.NO;
+ }
+
+ // read document-level field information
+ final String[] fieldMetas =
+ documentMeta.getValues(LuceneConstants.FIELD_PREFIX + fieldName);
+ if (fieldMetas.length != 0) {
+ for (final String val : fieldMetas) {
+ System.out.println( fieldName + " : " + val );
+ if (LuceneConstants.STORE_YES.equals(val)) {
+ store = Field.Store.YES;
+ } else if (LuceneConstants.STORE_NO.equals(val)) {
+ store = Field.Store.NO;
+ } else if (LuceneConstants.STORE_COMPRESS.equals(val)) {
+ compress = true;
+ } else if (LuceneConstants.INDEX_TOKENIZED.equals(val)) {
+ index = Field.Index.ANALYZED;
+ } else if (LuceneConstants.INDEX_NO.equals(val)) {
+ index = Field.Index.NO;
+ } else if (LuceneConstants.INDEX_UNTOKENIZED.equals(val)) {
+ index = Field.Index.NOT_ANALYZED;
+ } else if (LuceneConstants.INDEX_NO_NORMS.equals(val)) {
+ index = Field.Index.ANALYZED_NO_NORMS;
+ } else if (LuceneConstants.VECTOR_NO.equals(val)) {
+ vector = Field.TermVector.NO;
+ } else if (LuceneConstants.VECTOR_YES.equals(val)) {
+ vector = Field.TermVector.YES;
+ } else if (LuceneConstants.VECTOR_POS.equals(val)) {
+ vector = Field.TermVector.WITH_POSITIONS;
+ } else if (LuceneConstants.VECTOR_POS_OFFSET.equals(val)) {
+ vector = Field.TermVector.WITH_POSITIONS_OFFSETS;
+ } else if (LuceneConstants.VECTOR_OFFSET.equals(val)) {
+ vector = Field.TermVector.WITH_OFFSETS;
+ }
+ }
+ }
+
+ for (final String fieldValue : entry.getValue()) {
+ if ( compress )
+ {
+ out.add( new Field( fieldName, CompressionTools.compressString( fieldValue ), Field.Store.YES ) );
+ }
+ out.add(new Field(fieldName, fieldValue, store, index, vector));
+ }
+ }
+
+ return out;
+ }
+
+ @SuppressWarnings("unchecked")
+ private void processOptions(Configuration conf) {
+ final Iterator iterator = conf.iterator();
+ while (iterator.hasNext()) {
+ final String key = (String) ((Map.Entry)iterator.next()).getKey();
+ if (!key.startsWith(LuceneConstants.LUCENE_PREFIX)) {
+ continue;
+ }
+ if (key.startsWith(LuceneConstants.FIELD_STORE_PREFIX)) {
+ final String field =
+ key.substring(LuceneConstants.FIELD_STORE_PREFIX.length());
+ final LuceneWriter.STORE store = LuceneWriter.STORE.valueOf(conf.get(key));
+ switch (store) {
+ case YES:
+ fieldStore.put(field, Field.Store.YES);
+ break;
+ case NO:
+ fieldStore.put(field, Field.Store.NO);
+ break;
+ case COMPRESS:
+ fieldCompress.add(field);
+ break;
+ }
+ } else if (key.startsWith(LuceneConstants.FIELD_INDEX_PREFIX)) {
+ final String field =
+ key.substring(LuceneConstants.FIELD_INDEX_PREFIX.length());
+ final LuceneWriter.INDEX index = LuceneWriter.INDEX.valueOf(conf.get(key));
+ switch (index) {
+ case NO:
+ fieldIndex.put(field, Field.Index.NO);
+ break;
+ case NO_NORMS:
+ fieldIndex.put(field, Field.Index.NOT_ANALYZED_NO_NORMS);
+ break;
+ case TOKENIZED:
+ fieldIndex.put(field, Field.Index.ANALYZED);
+ break;
+ case UNTOKENIZED:
+ fieldIndex.put(field, Field.Index.NOT_ANALYZED);
+ break;
+ }
+ } else if (key.startsWith(LuceneConstants.FIELD_VECTOR_PREFIX)) {
+ final String field =
+ key.substring(LuceneConstants.FIELD_VECTOR_PREFIX.length());
+ final LuceneWriter.VECTOR vector = LuceneWriter.VECTOR.valueOf(conf.get(key));
+ switch (vector) {
+ case NO:
+ fieldVector.put(field, Field.TermVector.NO);
+ break;
+ case OFFSET:
+ fieldVector.put(field, Field.TermVector.WITH_OFFSETS);
+ break;
+ case POS:
+ fieldVector.put(field, Field.TermVector.WITH_POSITIONS);
+ break;
+ case POS_OFFSET:
+ fieldVector.put(field, Field.TermVector.WITH_POSITIONS_OFFSETS);
+ break;
+ case YES:
+ fieldVector.put(field, Field.TermVector.YES);
+ break;
+ }
+ }
+ }
+ }
+
+ public void open(JobConf job, String name)
+ throws IOException {
+ this.fs = FileSystem.get(job);
+ perm = new Path(FileOutputFormat.getOutputPath(job), name);
+ temp = job.getLocalPath("index/_" +
+ Integer.toString(new Random().nextInt()));
+
+ fs.delete(perm, true); // delete old, if any
+ analyzerFactory = new AnalyzerFactory(job);
+ writer = new IndexWriter(
+ FSDirectory.open(new File(fs.startLocalOutput(perm, temp).toString())),
+ new NutchDocumentAnalyzer(job), true, MaxFieldLength.UNLIMITED);
+
+ writer.setMergeFactor(job.getInt("indexer.mergeFactor", 10));
+ writer.setMaxBufferedDocs(job.getInt("indexer.minMergeDocs", 100));
+ writer.setMaxMergeDocs(job
+ .getInt("indexer.maxMergeDocs", Integer.MAX_VALUE));
+ writer.setTermIndexInterval(job.getInt("indexer.termIndexInterval", 128));
+ writer.setMaxFieldLength(job.getInt("indexer.max.tokens", 10000));
+ writer.setInfoStream(LogUtil.getDebugStream(Indexer.LOG));
+ writer.setUseCompoundFile(false);
+ writer.setSimilarity(new NutchSimilarity());
+
+ processOptions(job);
+ }
+
+ public void close() throws IOException {
+ writer.optimize();
+ writer.close();
+ fs.completeLocalOutput(perm, temp); // copy to dfs
+ fs.createNewFile(new Path(perm, Indexer.DONE_NAME));
+ }
+
+ public void write(NutchDocument doc) throws IOException {
+ final Document luceneDoc = createLuceneDoc(doc);
+ final NutchAnalyzer analyzer = analyzerFactory.get(luceneDoc.get("lang"));
+ if (Indexer.LOG.isDebugEnabled()) {
+ Indexer.LOG.debug("Indexing [" + luceneDoc.get("url")
+ + "] with analyzer " + analyzer + " (" + luceneDoc.get("lang")
+ + ")");
+ }
+ writer.addDocument(luceneDoc, analyzer);
+
+ }
+
+ /** Adds a lucene field.
+ * <p>
+ * This method is provided for backward-compatibility with
+ * older indexing filters. This should not be used by newer
+ * implementations since this is slower than
+ * {@link NutchDocument#add(String, String)} and will be removed
+ * in a future release.
+ * </p>
+ * @param f Lucene field to be added.
+ * @deprecated Use {@link NutchDocument#add(String, String)} instead and
+ * set index-level metadata for field information.
+ * */
+ @Deprecated
+ public static void add(NutchDocument doc, Field f) {
+ final String fieldName = f.name();
+ final String key = LuceneConstants.FIELD_PREFIX + fieldName;
+ final Metadata documentMeta = doc.getDocumentMeta();
+ if (f.isStored()) {
+ documentMeta.add(key, LuceneConstants.STORE_YES);
+ } else {
+ documentMeta.add(key, LuceneConstants.STORE_NO);
+ }
+
+ if (f.isIndexed()) {
+ if (f.isTokenized()) {
+ documentMeta.add(key, LuceneConstants.INDEX_TOKENIZED);
+ } else if (f.getOmitNorms()) {
+ documentMeta.add(key, LuceneConstants.INDEX_NO_NORMS);
+ } else {
+ documentMeta.add(key, LuceneConstants.INDEX_UNTOKENIZED);
+ }
+ } else {
+ documentMeta.add(key, LuceneConstants.INDEX_NO);
+ }
+
+ if (f.isStoreOffsetWithTermVector() && f.isStorePositionWithTermVector()) {
+ documentMeta.add(key, LuceneConstants.VECTOR_POS_OFFSET);
+ } else if (f.isStoreOffsetWithTermVector()) {
+ documentMeta.add(key, LuceneConstants.VECTOR_OFFSET);
+ } else if (f.isStorePositionWithTermVector()) {
+ documentMeta.add(key, LuceneConstants.VECTOR_POS);
+ } else if (f.isTermVectorStored()) {
+ documentMeta.add(key, LuceneConstants.VECTOR_YES);
+ } else {
+ documentMeta.add(key, LuceneConstants.VECTOR_NO);
+ }
+ }
+
+ public static void addFieldOptions(String field, LuceneWriter.STORE store,
+ LuceneWriter.INDEX index, LuceneWriter.VECTOR vector, Configuration conf) {
+
+ conf.set(LuceneConstants.FIELD_STORE_PREFIX + field, store.toString());
+ conf.set(LuceneConstants.FIELD_INDEX_PREFIX + field, index.toString());
+ conf.set(LuceneConstants.FIELD_VECTOR_PREFIX + field, vector.toString());
+ }
+
+ public static void addFieldOptions(String field, LuceneWriter.STORE store,
+ LuceneWriter.INDEX index, Configuration conf) {
+ LuceneWriter.addFieldOptions(field, store, index, LuceneWriter.VECTOR.NO, conf);
+ }
+}
Added: tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/plugin/PluginManifestParser.java
===================================================================
--- tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/plugin/PluginManifestParser.java (rev 0)
+++ tags/nutchwax-0_13-JIRA-WAX-75/archive/src/nutch/src/java/org/apache/nutch/plugin/PluginManifestParser.java 2010-07-11 00:09:27 UTC (rev 3168)
@@ -0,0 +1,326 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.nutch.plugin;
+
+import java.io.File;
+import java.io.IOException;
+import java.io.UnsupportedEncodingException;
+import java.net.MalformedURLException;
+import java.net.URL;
+import java.net.URLDecoder;
+import java.util.HashMap;
+import java.util.Map;
+
+import javax.xml.parsers.DocumentBuilder;
+import javax.xml.parsers.DocumentBuilderFactory;
+import javax.xml.parsers.ParserConfigurationException;
+
+import org.apache.commons.logging.Log;
+
+import org.apache.hadoop.conf.Configuration;
+import org.w3c.dom.Document;
+import org.w3c.dom.Element;
+import org.w3c.dom.Node;
+import org.w3c.dom.NodeList;
+import org.xml.sax.SAXException;
+
+/**
+ * The <code>PluginManifestParser</code> parser just parse the manifest file
+ * in all plugin directories.
+ *
+ * @author joa23
+ */
+public class PluginManifestParser {
+ private static final String ATTR_NAME = "name";
+ private static final String ATTR_CLASS = "class";
+ private static final String ATTR_ID = "id";
+
+ public static final Log LOG = PluginRepository.LOG;
+
+ private static final boolean WINDOWS = System.getProperty("os.name")
+ .startsWith("Windows");
+
+ private Configuration conf;
+
+ private PluginRepository pluginRepository;
+
+ public PluginManifestParser(Configuration conf,
+ PluginRepository pluginRepository) {
+ this.conf = conf;
+ this.pluginRepository = pluginRepository;
+ }
+
+ /**
+ * Returns a list of all found plugin descriptors.
+ *
+ * @param pluginFolders
+ * folders to search plugins from
+ * @return A {@link Map} of all found {@link PluginDescriptor}s.
+ */
+ public Map<String, PluginDescriptor> parsePluginFolder(String[] pluginFolders) {
+ Map<String, PluginDescriptor> map = new HashMap<String, PluginDescriptor>();
+
+ if (pluginFolders == null) {
+ throw new IllegalArgumentException("plugin.folders is not defined");
+ }
+
+ for (String name : pluginFolders) {
+ File directory = getPluginFolder(name);
+ if (directory == null) {
+ continue;
+ }
+ LOG.info("Plugins: looking in: " + directory.getAbsolutePath());
+ for (File oneSubFolder : directory.listFiles()) {
+ if (oneSubFolder.isDirectory()) {
+ String manifestPath = oneSubFolder.getAbsolutePath() + File.separator
+ + "plugin.xml";
+ try {
+ LOG.debug("parsing: " + manifestPath);
+ PluginDescriptor p = parseManifestFile(manifestPath);
+ map.put(p.getPluginId(), p);
+ } catch (MalformedURLException e) {
+ LOG.warn(e.toString());
+ } catch (SAXException e) {
+ LOG.warn(e.toString());
+ } catch (IOException e) {
+ LOG.warn(e.toString());
+ } catch (ParserConfigurationException e) {
+ LOG.warn(e.toString());
+ }
+ }
+ }
+ }
+ return map;
+ }
+
+ /**
+ * Return the named plugin folder. If the name is absolute then it is
+ * returned. Otherwise, for relative names, the classpath is scanned.
+ */
+ public File getPluginFolder(String name) {
+ File directory = new File(name);
+ if (!directory.isAbsolute()) {
+ URL url = PluginManifestParser.class.getClassLoader().getResource(name);
+ if (url == null && directory.exists() && directory.isDirectory()
+ && directory.listFiles().length > 0) {
+ return directory; // relative path that is not in the classpath
+ } else if (url == null) {
+ LOG.warn("Plugins: directory not found: " + name);
+ return null;
+ } else if ( "jar".equals(url.getProtocol()) ) {
+ try
+ {
+ // HACK to find directory containing .jar file and look for plugins there.
+ LOG.warn( "HACK to look for plugin directory next to jar file: " + url );
+ java.net.JarURLConnection connection = (java.net.JarURLConnection) url.openConnection();
+ URL url2 = connection.getJarFileURL();
+ if ( !"file".equals(url2.getProtocol()) )
+ {
+ LOG.warn( "Jar file is not a file: " + url2 );
+ return null;
+ }
+ directory = new File( new File( url2.getFile() ).getParent( ) + "/" + name );
+ LOG.warn( "Plugin directory: " + directory );
+ return directory;
+ }
+ catch ( IOException ioe )
+ {
+ LOG.warn( ioe );
+ return null;
+ }
+ } else if (!"file".equals(url.getProtocol())) {
+ LOG.warn("Plugins: not a file: url. Can't load plugins from: " + url);
+ return null;
+ }
+ String path = url.getPath();
+ if (WINDOWS && path.startsWith("/")) // patch a windows bug
+ path = path.substring(1);
+ try {
+ path = URLDecoder.decode(path, "UTF-8"); // decode the url path
+ } catch (UnsupportedEncodingException e) {
+ }
+ directory = new File(path);
+ }
+ return directory;
+ }
+
+ /**
+ * @param manifestPath
+ * @throws ParserConfigurationException
+ * @throws IOException
+ * @throws SAXException
+ * @throws MalformedURLException
+ */
+ private PluginDescriptor parseManifestFile(String pManifestPath)
+ throws MalformedURLException, SAXException, IOException,
+ ParserConfigurationException {
+ Document document = parseXML(new File(pManifestPath).toURL());
+ String pPath = new File(pManifestPath).getParent();
+ return parsePlugin(document, pPath);
+ }
+
+ /**
+ * @param url
+ * @return Document
+ * @throws IOException
+ * @throws SAXException
+ * @throws ParserConfigurationException
+ * @throws DocumentException
+ */
+ private Document parseXML(URL url) throws SAXException, IOException,
+ ParserConfigurationException {
+ DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
+ DocumentBuilder builder = factory.newDocumentBuilder();
+ return builder.parse(url.openStream());
+ }
+
+ /**
+ * @param pDocument
+ * @throws MalformedURLException
+ */
+ private PluginDescriptor parsePlugin(Document pDocument, String pPath)
+ throws MalformedURLException {
+ Element rootElement = pDocument.getDocumentElement();
+ String id = rootElement.getAttribute(ATTR_ID);
+ String name = rootElement.getAttribute(ATTR_NAME);
+ String version = rootElement.getAttribute("version");
+ String providerName = rootElement.getAttribute("provider-name");
+ String pluginClazz = null;
+ if (rootElement.getAttribute(ATTR_CLASS).trim().length() > 0) {
+ pluginClazz = rootElement.getAttribute(ATTR_CLASS);
+ }
+ PluginDescriptor pluginDescriptor = new PluginDescriptor(id, version, name,
+ providerName, pluginClazz, pPath, this.conf);
+ LOG.debug("plugin: id=" + id + " name=" + name + " version=" + version
+ + " provider=" + providerName + "class=" + pluginClazz);
+ parseExtension(rootElement, pluginDescriptor);
+ parseExtensionPoints(rootElement, pluginDescriptor);
+ parseLibraries(rootElement, pluginDescriptor);
+ parseRequires(rootElement, pluginDescriptor);
+ return pluginDescriptor;
+ }
+
+ /**
+ * @param pRootElement
+ * @param pDescriptor
+ * @throws MalformedURLException
+ */
+ private void parseRequires(Element pRootElement, PluginDescriptor pDescriptor)
+ throws MalformedURLException {
+
+ NodeList nodelist = pRootElement.getElementsByTagName("requires");
+ if (nodelist.getLength() > 0) {
+
+ Element requires = (Element) nodelist.item(0);
+
+ NodeList imports = requires.getElementsByTagName("import");
+ for (int i = 0; i < imports.getLength(); i++) {
+ Element anImport = (Element) imports.item(i);
+ String plugin = anImport.getAttribute("plugin");
+ if (plugin != null) {
+ pDescriptor.addDependency(plugin);
+ }
+ }
+ }
+ }
+
+ /**
+ * @param pRootElement
+ * @param pDescriptor
+ * @throws MalformedURLException
+ */
+ private void parseLibraries(Element pRootElement, PluginDescriptor pDescriptor)
+ throws MalformedURLException {
+ NodeList nodelist = pRootElement.getElementsByTagName("runtime");
+ if (nodelist.getLength() > 0) {
+
+ Element runtime = (Element) nodelist.item(0);
+
+ NodeList libraries = runtime.getElementsByTagName("library");
+ for (int i = 0; i < libraries.getLength(); i++)...
[truncated message content] |
|
From: <bi...@us...> - 2010-07-10 23:34:31
|
Revision: 3167
http://archive-access.svn.sourceforge.net/archive-access/?rev=3167&view=rev
Author: binzino
Date: 2010-07-10 23:34:25 +0000 (Sat, 10 Jul 2010)
Log Message:
-----------
Create tag/branch for this JIRA.
Added Paths:
-----------
tags/nutchwax-0_13-JIRA-WAX-75/
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bra...@us...> - 2010-07-06 22:23:38
|
Revision: 3166
http://archive-access.svn.sourceforge.net/archive-access/?rev=3166&view=rev
Author: bradtofel
Date: 2010-07-06 22:23:32 +0000 (Tue, 06 Jul 2010)
Log Message:
-----------
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/exception/HTMLError.jsp
Modified: trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/exception/HTMLError.jsp
===================================================================
--- trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/exception/HTMLError.jsp 2010-07-06 22:22:12 UTC (rev 3165)
+++ trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/exception/HTMLError.jsp 2010-07-06 22:23:32 UTC (rev 3166)
@@ -1,7 +1,9 @@
<%@ page language="java" pageEncoding="utf-8" contentType="text/html;charset=utf-8"%>
<%@ page import="java.util.List" %>
<%@ page import="java.util.Date" %>
+<%@ page import="java.util.Iterator" %>
<%@ page import="org.archive.wayback.exception.WaybackException" %>
+<%@ page import="org.archive.wayback.ResultURIConverter" %>
<%@ page import="org.archive.wayback.exception.ResourceNotInArchiveException"%>
<%@ page import="org.archive.wayback.exception.ResourceNotAvailableException"%>
<%@ page import="org.archive.wayback.core.CaptureSearchResult" %>
@@ -29,17 +31,39 @@
StringFormatter fmt = results.getWbRequest().getFormatter();
%>
+<jsp:include page="/WEB-INF/global-template/UI-header.jsp" flush="true" />
-<h2><%= fmt.format(e.getTitleKey()) %></h2>
-<p><b><%= fmt.format(e.getMessageKey(),e.getMessage()) %></b></p>
+ <div id="positionHome">
+ <section>
+ <div id="logoHome">
+ <h1><span>Internet Archive's Wayback Machine</span></h1>
+ </div>
+ </section>
+ <section>
+ <div id="searchHome">
+ <form name="form1" method="get" action="<%= queryPrefix %>query">
+ <input type="hidden" name="<%= WaybackRequest.REQUEST_TYPE %>" value="<%= WaybackRequest.REQUEST_CAPTURE_QUERY %>">
+ <input type="text" name="<%= WaybackRequest.REQUEST_URL %>" value="http://" size="40">
+ <button type="submit" name="Submit">Go Wayback!</button>
+ </form>
+ <div id="searchAdvHome">
+ <a href="[ADVANCED SEARCH]">Advanced Search</a>
+ </div>
+ </div>
+ </section>
+ <section>
+ <div id="error">
+
+ <h2><%= fmt.format(e.getTitleKey()) %></h2>
+ <p><%= fmt.format(e.getMessageKey(),e.getMessage()) %></p>
<%
if(e instanceof ResourceNotInArchiveException) {
ResourceNotInArchiveException niae = (ResourceNotInArchiveException) e;
List<String> closeMatches = niae.getCloseMatches();
if(closeMatches != null && !closeMatches.isEmpty()) {
%>
- <p>
- Other possible close matches to try:<br></br>
+ <p>Other possible close matches to try:</p>
+ <p>
<%
WaybackRequest tmp = wbr.clone();
for(String closeMatch : closeMatches) {
@@ -47,7 +71,7 @@
String link = queryPrefix + "query?" +
tmp.getQueryArguments();
%>
- <a href="<%= link %>"><%= closeMatch %></a><br>
+ <a href="<%= link %>"><%= closeMatch %></a><br/>
<%
}
}
@@ -61,46 +85,58 @@
String escapedLink = fmt.escapeHtml(link);
String escapedParentUrl = fmt.escapeHtml(parentUrl);
%>
- </p>
- <p>
- More options:<br></br>
- Try Searching all pages under <a href="<%= escapedLink %>"><%= escapedParentUrl %></a>
- </p>
+ </p>
+ <p>More options:</p>
+ <p>Try Searching all pages under <a href="<%= escapedLink %>"><%= escapedParentUrl %></a></p>
<%
}
} else if(e instanceof ResourceNotAvailableException) {
%>
<div class="wm-nav-link-div">
<%
- CaptureSearchResults cResults = results.getCaptureResults();
- Date firstDate = cResults.getFirstResultDate();
- Date lastDate = cResults.getLastResultDate();
- PartitionPartitionMap yearMap =
- new PartitionPartitionMap();
- PartitionSize yearSize = Partitioner.yearSize;
- Partitioner<Partition<CaptureSearchResult>> yearPartitioner =
- new Partitioner<Partition<CaptureSearchResult>>(yearMap);
-
- List<Partition<Partition<CaptureSearchResult>>> yearPartitions =
- yearPartitioner.getRange(yearSize,firstDate,lastDate);
-
- String navs[] = PartitionsToGraph.getNavigators(fmt,results.getResult());
- String links[] = PartitionsToGraph.getNavigatorLinks(yearPartitions,results.getURIConverter());
- String searchUrl = wbr.getRequestUrl();
- String starLink = fmt.escapeHtml(queryPrefix + "*/" + searchUrl);
- links[PartitionsToGraph.NAV_CURRENT] = starLink;
- for(int i = 0; i < navs.length; i++) {
- if(i > 0) {
- %> <%
- }
- if(links[i] == null) {
- %><%= navs[i] %><%
- } else {
- %> <a href="<%= links[i] %>"><%= navs[i] %></a> <%
- }
+ ResourceNotAvailableException rnae = (ResourceNotAvailableException) e;
+
+ CaptureSearchResults cResults = rnae.getCaptureSearchResults();
+ Iterator<CaptureSearchResult> itr = cResults.iterator();
+ CaptureSearchResult prev = null;
+ CaptureSearchResult next = null;
+ while(itr.hasNext()) {
+ CaptureSearchResult cur = itr.next();
+ if(cur.isClosest()) {
+ break;
}
+ prev = cur;
+ }
+ if(itr.hasNext()) {
+ next = itr.next();
+ }
+ if((prev != null) || (next != null)) {
+ String dateFormat = "{0,date,MMMM dd, yyyy HH:mm:ss}";
+ ResultURIConverter conv = wbr.getAccessPoint().getUriConverter();
+ %>
+ <div>Or try another close version:</div>
+ <%
+ if(prev != null) {
+ String safePrevReplay = fmt.escapeHtml(conv.makeReplayURI(prev.getCaptureTimestamp(),prev.getOriginalUrl()));
+ %>
+ <div>Previous:<a href="<%= safePrevReplay %>"><%= fmt.format(dateFormat,prev.getCaptureDate())%></a></div>
+ <%
+ }
+ if(next != null) {
+ String safeNextReplay = fmt.escapeHtml(conv.makeReplayURI(next.getCaptureTimestamp(),next.getOriginalUrl()));
+ %>
+ <div>Next:<a href="<%= safeNextReplay %>"><%= fmt.format(dateFormat,next.getCaptureDate())%></a></div>
+ <%
+ }
+ }
%>
</div>
<%
}
%>
+
+ </div>
+ </section>
+ <div id="errorBorder"></div>
+
+<jsp:include page="/WEB-INF/global-template/UI-footer.jsp" flush="true" />
\ No newline at end of file
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bra...@us...> - 2010-07-06 22:22:18
|
Revision: 3165
http://archive-access.svn.sourceforge.net/archive-access/?rev=3165&view=rev
Author: bradtofel
Date: 2010-07-06 22:22:12 +0000 (Tue, 06 Jul 2010)
Log Message:
-----------
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/query/HTMLUrlResults.jsp
Modified: trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/query/HTMLUrlResults.jsp
===================================================================
--- trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/query/HTMLUrlResults.jsp 2010-07-06 22:17:28 UTC (rev 3164)
+++ trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/query/HTMLUrlResults.jsp 2010-07-06 22:22:12 UTC (rev 3165)
@@ -9,7 +9,9 @@
%><%@ page import="org.archive.wayback.core.UrlSearchResults"
%><%@ page import="org.archive.wayback.core.WaybackRequest"
%><%@ page import="org.archive.wayback.util.StringFormatter"
-%><%
+%>
+<jsp:include page="/WEB-INF/global-template/UI-header.jsp" flush="true" />
+<%
UIResults results = UIResults.extractUrlQuery(request);
WaybackRequest wbRequest = results.getWbRequest();
UrlSearchResults uResults = results.getUrlResults();
@@ -17,9 +19,10 @@
StringFormatter fmt = wbRequest.getFormatter();
String searchString = wbRequest.getRequestUrl();
+String staticPrefix = results.getStaticPrefix();
+String queryPrefix = results.getQueryPrefix();
+String replayPrefix = results.getReplayPrefix();
-
-
Date searchStartDate = wbRequest.getStartDate();
Date searchEndDate = wbRequest.getEndDate();
@@ -29,11 +32,94 @@
long totalCaptures = uResults.getMatchingCount();
%>
-<%= fmt.format("PathPrefixQuery.showingResults",firstResult + 1,lastResult,
- totalCaptures,searchString) %>
-<br/>
+<script src="http://ajax.googleapis.com/ajax/libs/jquery/1.4.2/jquery.min.js" type="text/javascript"></script>
+<script src="http://ajax.googleapis.com/ajax/libs/jqueryui/1.8.1/jquery-ui.min.js" type="text/javascript"></script>
+<script type="text/javascript" src="<%= staticPrefix %>js/jquery.dataTables.min.js" charset="utf-8"></script>
+<script type="text/javascript">
+$().ready(function(){
+ $(".dataTables_processing").show();
+ $('#resultsUrl th.url span').html(' ↑');
+ $('#resultsUrl th').mouseup(function(){
+ \$('#resultsUrl th span').html('');
+ \$(this).find('span').html(' ↑');
+ if (\$(this).hasClass('sorting_asc')) {
+ \$(this).find('span').html(' ↓');
+ } else if (\$(this).hasClass('sorting_desc')) {
+ \$(this).find('span').html(' ↑');
+ };
+ });
+ var rowCount = \$('#resultsUrl tbody tr').length;
+ if (rowCount < 50) {
+ \$('#resultsUrl').dataTable({
+ "bProcessing": true,
+ "aoColumns": [{"sType":"html"},{"sType":"date"},{"sType":"date"},null,null,null],
+ "aaSorting": [ [0,'asc'] ],
+ "bPaginate": false,
+ "bInfo": false,
+ "bFilter": true,
+ "bStateSave": true,
+ "bAutoWidth": false,
+ "oLanguage": {
+ "sSearch": "Filter results (i.e. '.txt'):"
+ }
+ });
+ } else {
+ \$('#resultsUrl').dataTable({
+ "bProcessing": true,
+ "aoColumns": [{"sType":"html"},{"sType":"date"},{"sType":"date"},null,null,null],
+ "aaSorting": [ [0,'asc'] ],
+ "bPaginate": true,
+ "bInfo": true,
+ "sPaginationType": "full_numbers",
+ "bFilter": true,
+ "bStateSave": true,
+ "bAutoWidth": false,
+ "oLanguage": {
+ "sSearch": "Filter results (i.e. '.txt'):"
+ },
+ "iDisplayLength": 50
+ });
+ }
+ });
+$(window).load(function(){
-<hr></hr>
+});
+</script>
+ <div id="positionHome">
+ <section>
+ <div id="logoHome">
+ <h1><span>Internet Archive's Wayback Machine</span></h1>
+ </div>
+ </section>
+ <section>
+ <div id="searchHome">
+ <form name="form1" method="get" action="<%= queryPrefix %>query">
+ <input type="hidden" name="<%= WaybackRequest.REQUEST_TYPE %>" value="<%= WaybackRequest.REQUEST_CAPTURE_QUERY %>">
+ <input type="text" name="<%= WaybackRequest.REQUEST_URL %>" value="http://" size="40">
+ <button type="submit" name="Submit">Go Wayback!</button>
+ </form>
+ <div id="searchAdvHome">
+ <a href="[ADVANCED SEARCH]">Advanced Search</a>
+ </div>
+ </div>
+ </section>
+ </div>
+ <div id="positionTable">
+
+ <h2 class="green"><%= fmt.format("PathPrefixQuery.showingResults",totalCaptures) %></h2>
+
+ <table id="resultsUrl">
+ <thead>
+ <tr>
+ <th class="url">URL<span></span></th>
+ <th>From<span></span></th>
+ <th>To<span></span></th>
+ <th>Captures<span></span></th>
+ <th>Duplicates<span></span></th>
+ <th>Uniques<span></span></th>
+ </tr>
+ </thead>
+ <tbody>
<%
Iterator<UrlSearchResult> itr = uResults.iterator();
while(itr.hasNext()) {
@@ -45,6 +131,7 @@
String lastDateTSss = result.getLastCaptureTimestamp();
long numCaptures = result.getNumCaptures();
long numVersions = result.getNumVersions();
+ long numDupes = result.getNumCaptures() - result.getNumVersions();
Date firstDate = result.getFirstCaptureDate();
Date lastDate = result.getLastCaptureDate();
@@ -53,9 +140,17 @@
String ts = result.getFirstCaptureTimestamp();
String anchor = uriConverter.makeReplayURI(ts,originalUrl);
%>
- <a onclick="SetAnchorDate('<%= ts %>');" href="<%= anchor %>">
- <%= urlKey %>
- </a>
+ <tr>
+ <td class="url">
+ <a onclick="SetAnchorDate('<%= ts %>');" href="<%= anchor %>"><%= urlKey %></a>
+ </td>
+ <td class="dateFrom"><%= fmt.format("PathPrefixQuery.captureDate",firstDate) %></td>
+ <td class="dateTo"><%= fmt.format("PathPrefixQuery.captureDate",lastDate) %></td>
+ <td class="captures"><%= numCaptures %></td>
+ <td class="dupes"><%= numDupes %></td>
+ <td class="uniques"><%= numVersions %></td>
+ </tr>
+ <!--
<span class="mainSearchText">
<%= fmt.format("PathPrefixQuery.versionCount",numVersions) %>
</span>
@@ -63,11 +158,23 @@
<span class="mainSearchText">
<%= fmt.format("PathPrefixQuery.singleCaptureDate",firstDate) %>
</span>
+ -->
<%
} else {
String anchor = results.makeCaptureQueryUrl(originalUrl);
%>
+ <tr>
+ <td class="url">
+ <a href="<%= anchor %>"><%= urlKey %></a>
+ </td>
+ <td class="dateFrom"><%= fmt.format("PathPrefixQuery.captureDate",firstDate) %></td>
+ <td class="dateTo"><%= fmt.format("PathPrefixQuery.captureDate",lastDate) %></td>
+ <td class="captures"><%= numCaptures %></td>
+ <td class="dupes"><%= numDupes %></td>
+ <td class="uniques"><%= numVersions %></td>
+ </tr>
+ <!--
<a href="<%= anchor %>">
<%= urlKey %>
</a>
@@ -78,11 +185,10 @@
<span class="mainSearchText">
<%= fmt.format("PathPrefixQuery.multiCaptureDate",numCaptures,firstDate,lastDate) %>
</span>
+ -->
<%
}
%>
- <br/>
- <br/>
<%
}
@@ -90,12 +196,11 @@
int curPage = uResults.getCurPageNum();
if(curPage > uResults.getNumPages()) {
%>
- <hr></hr>
<a href="<%= results.urlForPage(1) %>">First results</a>
<%
} else if(uResults.getNumPages() > 1) {
%>
- <hr></hr>
+
<%
for(int i = 1; i <= uResults.getNumPages(); i++) {
if(i == curPage) {
@@ -109,4 +214,9 @@
}
}
}
-%>
\ No newline at end of file
+%>
+ </tbody>
+ </table>
+
+
+<jsp:include page="/WEB-INF/global-template/UI-footer.jsp" flush="true" />
\ No newline at end of file
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bra...@us...> - 2010-07-06 22:17:35
|
Revision: 3164
http://archive-access.svn.sourceforge.net/archive-access/?rev=3164&view=rev
Author: bradtofel
Date: 2010-07-06 22:17:28 +0000 (Tue, 06 Jul 2010)
Log Message:
-----------
tweaks
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/replay/Toolbar.jsp
trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/replay/UrlRedirectNotice.jsp
Modified: trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/replay/Toolbar.jsp
===================================================================
--- trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/replay/Toolbar.jsp 2010-06-24 20:27:18 UTC (rev 3163)
+++ trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/replay/Toolbar.jsp 2010-07-06 22:17:28 UTC (rev 3164)
@@ -174,7 +174,7 @@
<table style="border-collapse:collapse;margin:0 auto;padding:0;width:570px;"><tbody><tr>
<td style="padding:3px 0;" colspan="2">
- <form target="_top" method="get" action="<%= queryPrefix %>query" name="wmtb" id="wmtb" style="margin:0!important;padding:0!important;"><input type="text" name="<%= WaybackRequest.REQUEST_URL %>" id="wmtbURL" value="<%= searchUrlSafe %>" style="width:400px;font-size:11px;font-family:'Lucida Grande','Arial',sans-serif;"/><input type="hidden" name="<%= WaybackRequest.REQUEST_TYPE %>" value="<%= WaybackRequest.REQUEST_REPLAY_QUERY %>"><input type="submit" value="Go" style="font-size:11px;font-family:'Lucida Grande','Arial',sans-serif;margin-left:5px;"/><span id="wm_tb_options" style="display:block;"></span></form>
+ <form target="_top" method="get" action="<%= queryPrefix %>query" name="wmtb" id="wmtb" style="margin:0!important;padding:0!important;"><input type="text" name="<%= WaybackRequest.REQUEST_URL %>" id="wmtbURL" value="<%= searchUrlSafe %>" style="width:400px;font-size:11px;font-family:'Lucida Grande','Arial',sans-serif;"/><input type="hidden" name="<%= WaybackRequest.REQUEST_TYPE %>" value="<%= WaybackRequest.REQUEST_REPLAY_QUERY %>"><input type="hidden" name="<%= WaybackRequest.REQUEST_DATE %>" value="<%= data.curResult.getCaptureTimestamp() %>"><input type="submit" value="Go" style="font-size:11px;font-family:'Lucida Grande','Arial',sans-serif;margin-left:5px;"/><span id="wm_tb_options" style="display:block;"></span></form>
</td>
<td style="vertical-align:bottom;padding:5px 0 0 0!important;" rowspan="2">
<table style="border-collapse:collapse;width:110px;color:#99a;font-family:'Helvetica','Lucida Grande','Arial',sans-serif;"><tbody>
@@ -312,7 +312,7 @@
</td>
<td style="text-align:right;padding:5px;width:65px;font-size:11px!important;">
<a href="javascript:;" onclick="document.getElementById('wm-ipp').style.display='none';" style="display:block;padding-right:18px;background:url(<%= staticPrefix %>images/toolbar/wm_tb_close.png) no-repeat 100% 0;color:#33f;font-family:'Lucida Grande','Arial',sans-serif;margin-bottom:23px;" title="<%= fmt.format("ToolBar.closeTitle") %>"><%= fmt.format("ToolBar.closeText") %></a>
- <a href="FAQ" style="display:block;padding-right:18px;background:url(<%= staticPrefix %>images/toolbar/wm_tb_help.png) no-repeat 100% 0;color:#33f;font-family:'Lucida Grande','Arial',sans-serif;" title="<%= fmt.format("ToolBar.helpTitle") %>"><%= fmt.format("ToolBar.helpText") %></a>
+ <a href="https://webarchive.jira.com/wiki/display/WWMOS/FAQs" style="display:block;padding-right:18px;background:url(<%= staticPrefix %>images/toolbar/wm_tb_help.png) no-repeat 100% 0;color:#33f;font-family:'Lucida Grande','Arial',sans-serif;" title="<%= fmt.format("ToolBar.helpTitle") %>"><%= fmt.format("ToolBar.helpText") %></a>
</td>
</tr></tbody></table>
Modified: trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/replay/UrlRedirectNotice.jsp
===================================================================
--- trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/replay/UrlRedirectNotice.jsp 2010-06-24 20:27:18 UTC (rev 3163)
+++ trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/replay/UrlRedirectNotice.jsp 2010-07-06 22:17:28 UTC (rev 3164)
@@ -35,19 +35,30 @@
int secs = 5;
%>
+ <jsp:include page="/WEB-INF/global-template/UI-header.jsp" flush="true" />
+
+ <div id="positionHome">
+ <section>
+ <div id="logoHome">
+ <h1><span>Internet Archive's Wayback Machine</span></h1>
+ </div>
+ </section>
+ <section>
+ <div id="error">
<script type="text/javascript">
function go() {
document.location.href = "<%= safeTargetReplayUrlJS %>";
}
window.setTimeout("go()",<%= secs * 1000 %>);
</script>
- <h2>Following redirect...</h2>
- <p>The URL you requested:</p>
- <p><%= safeSource %></p>
- <p>redirected to the URL:</p>
+ <p class="code">Loading...</p>
+ <p class="code shift"><%= safeSource %> | <%= prettyDate %></p>
+ <p class="code shift red">Got an HTTP 302 response at crawl time</p>
+ <p class="code">Redirecting to...</p>
<p><%= safeTarget %></p>
- <p>
- when it was crawled at <%= prettyDate %>. You will be redirected
- to that target in <%= secs %> seconds.
- Click <a href="<%= safeTargetReplayUrl %>">here</a> to go now.
- </p>
+ <p class="impatient"><a href="<%= safeTargetReplayUrl %>">Impatient?</a></p>
+ </div>
+ </section>
+ <div id="errorBorder"></div>
+
+ <jsp:include page="/WEB-INF/global-template/UI-footer.jsp" flush="true" />
\ No newline at end of file
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bra...@us...> - 2010-06-24 20:27:24
|
Revision: 3163
http://archive-access.svn.sourceforge.net/archive-access/?rev=3163&view=rev
Author: bradtofel
Date: 2010-06-24 20:27:18 +0000 (Thu, 24 Jun 2010)
Log Message:
-----------
BUGFIX(unreported) need different Recorder filename for each Thread..
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/liveweb/URLtoARCCacher.java
Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/liveweb/URLtoARCCacher.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/liveweb/URLtoARCCacher.java 2010-06-24 20:26:25 UTC (rev 3162)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/liveweb/URLtoARCCacher.java 2010-06-24 20:27:18 UTC (rev 3163)
@@ -116,8 +116,8 @@
// to track if we got a response (any response) or an exception.
boolean gotUrl = false;
-
- Recorder recorder = new Recorder(recorderCacheDir,backingFileBase,
+ String fName = backingFileBase + "-" + Thread.currentThread().getId();
+ Recorder recorder = new Recorder(recorderCacheDir,fName,
outBufferSize, inBufferSize);
ExtendedGetMethod getMethod = null;
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bra...@us...> - 2010-06-24 20:26:31
|
Revision: 3162
http://archive-access.svn.sourceforge.net/archive-access/?rev=3162&view=rev
Author: bradtofel
Date: 2010-06-24 20:26:25 +0000 (Thu, 24 Jun 2010)
Log Message:
-----------
FEATURE: now adds HTTP "Authorization" header to the WaybackRequest
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/core/WaybackRequest.java
Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/core/WaybackRequest.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/core/WaybackRequest.java 2010-06-24 20:25:21 UTC (rev 3161)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/core/WaybackRequest.java 2010-06-24 20:26:25 UTC (rev 3162)
@@ -324,6 +324,10 @@
* see HttpServletRequest.getRemoteUser()
*/
public static final String REQUEST_REMOTE_USER = "requestremoteuser";
+ /**
+ * Exact value from HTTP request for header "Authorization"
+ */
+ public static final String REQUEST_AUTHORIZATION = "Authorization";
/**
* User Locale name: Best Guess at users requested locale.
@@ -866,6 +870,9 @@
putUnlessNull(REQUEST_WAYBACK_HOSTNAME, httpRequest.getLocalName());
putUnlessNull(REQUEST_AUTH_TYPE, httpRequest.getAuthType());
putUnlessNull(REQUEST_REMOTE_USER, httpRequest.getRemoteUser());
+
+ putUnlessNull(REQUEST_AUTHORIZATION,
+ httpRequest.getHeader(REQUEST_AUTHORIZATION));
putUnlessNull(REQUEST_WAYBACK_PORT,
String.valueOf(httpRequest.getLocalPort()));
putUnlessNull(REQUEST_WAYBACK_CONTEXT, httpRequest.getContextPath());
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bra...@us...> - 2010-06-24 20:25:27
|
Revision: 3161
http://archive-access.svn.sourceforge.net/archive-access/?rev=3161&view=rev
Author: bradtofel
Date: 2010-06-24 20:25:21 +0000 (Thu, 24 Jun 2010)
Log Message:
-----------
BUGFIX:(unreported) was not correctly handling empty/null datespec
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/ArchivalUrl.java
Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/ArchivalUrl.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/ArchivalUrl.java 2010-06-24 20:24:09 UTC (rev 3160)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/ArchivalUrl.java 2010-06-24 20:25:21 UTC (rev 3161)
@@ -69,9 +69,15 @@
}
public String toString(String datespec, String url) {
+ int dateLen = 0;
+ if(datespec != null) {
+ dateLen = datespec.length();
+ }
StringBuilder sb =
- new StringBuilder(url.length() + datespec.length()+10);
- sb.append(datespec);
+ new StringBuilder(url.length() + dateLen +10);
+ if(dateLen > 0) {
+ sb.append(datespec);
+ }
if(wbRequest.isCSSContext()) {
sb.append(ArchivalUrlRequestParser.CSS_CONTEXT);
sb.append(ArchivalUrlRequestParser.FLAG_DELIM);
@@ -88,7 +94,9 @@
sb.append(ArchivalUrlRequestParser.IDENTITY_CONTEXT);
sb.append(ArchivalUrlRequestParser.FLAG_DELIM);
}
- sb.append("/");
+ if(dateLen > 0) {
+ sb.append("/");
+ }
sb.append(UrlOperations.stripDefaultPortFromUrl(url));
return sb.toString();
}
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
Revision: 3160
http://archive-access.svn.sourceforge.net/archive-access/?rev=3160&view=rev
Author: bradtofel
Date: 2010-06-24 20:24:09 +0000 (Thu, 24 Jun 2010)
Log Message:
-----------
BUGFIX(unreported) bad "if" logic...
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/requestparser/ArchivalUrlFormRequestParser.java
Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/requestparser/ArchivalUrlFormRequestParser.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/requestparser/ArchivalUrlFormRequestParser.java 2010-06-24 20:23:06 UTC (rev 3159)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/requestparser/ArchivalUrlFormRequestParser.java 2010-06-24 20:24:09 UTC (rev 3160)
@@ -50,7 +50,7 @@
WaybackRequest wbRequest = super.parse(httpRequest, accessPoint);
if(wbRequest != null) {
String replayTimestamp = wbRequest.getReplayTimestamp();
- if((replayTimestamp != null) && replayTimestamp.length() == 0) {
+ if((replayTimestamp == null) || replayTimestamp.length() == 0) {
// lets call it a star query:
// TODO: should we clone?
wbRequest.setStartTimestamp(null);
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
Revision: 3159
http://archive-access.svn.sourceforge.net/archive-access/?rev=3159&view=rev
Author: bradtofel
Date: 2010-06-24 20:23:06 +0000 (Thu, 24 Jun 2010)
Log Message:
-----------
FEATURE: Unable to use Tomcat's built-in authorization - it's either all or nothing, so doesn't allow no-password access to certain IP range blocks. Now this class parses the users "Authorization" HTTP header to extract BASIC credentials.
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/authenticationcontrol/HTTPAuthBooleanOperator.java
Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/authenticationcontrol/HTTPAuthBooleanOperator.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/authenticationcontrol/HTTPAuthBooleanOperator.java 2010-06-22 19:15:59 UTC (rev 3158)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/authenticationcontrol/HTTPAuthBooleanOperator.java 2010-06-24 20:23:06 UTC (rev 3159)
@@ -25,6 +25,8 @@
package org.archive.wayback.authenticationcontrol;
import java.util.List;
+import java.io.UnsupportedEncodingException;
+import org.apache.commons.codec.binary.Base64;
import org.archive.wayback.core.WaybackRequest;
import org.archive.wayback.util.operator.BooleanOperator;
@@ -41,12 +43,32 @@
if(allowedUsers == null) {
return false;
}
- String currentUser = value.getRemoteUser();
+ String currentUser = getHTTPAuth(value);
if(currentUser == null) {
return false;
}
return allowedUsers.contains(currentUser);
}
+ private String decodeBasic(String authHeaderValue) {
+ if(authHeaderValue != null) {
+ if(authHeaderValue.startsWith("Basic ")) {
+ String b64 = authHeaderValue.substring(6);
+ byte[] decoded = Base64.decodeBase64(b64.getBytes());
+ try {
+ return new String(decoded,"utf-8");
+ } catch (UnsupportedEncodingException e) {
+ // really?...
+ return new String(decoded);
+ }
+ }
+ }
+ return null;
+
+ }
+ private String getHTTPAuth(WaybackRequest request) {
+ return decodeBasic(request.get("Authorization"));
+ }
+
/**
* @return the List of users that this operator matches against.
*/
@@ -55,6 +77,7 @@
}
/**
* @param allowedUsers the List of users that this operator matches against.
+ * format for values is "username:password"
*/
public void setAllowedUsers(List<String> allowedUsers) {
this.allowedUsers = allowedUsers;
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bra...@us...> - 2010-06-22 19:16:06
|
Revision: 3158
http://archive-access.svn.sourceforge.net/archive-access/?rev=3158&view=rev
Author: bradtofel
Date: 2010-06-22 19:15:59 +0000 (Tue, 22 Jun 2010)
Log Message:
-----------
cleanup, some polish
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/replay/Toolbar.jsp
Modified: trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/replay/Toolbar.jsp
===================================================================
--- trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/replay/Toolbar.jsp 2010-06-18 00:39:52 UTC (rev 3157)
+++ trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/replay/Toolbar.jsp 2010-06-22 19:15:59 UTC (rev 3158)
@@ -178,67 +178,72 @@
</td>
<td style="vertical-align:bottom;padding:5px 0 0 0!important;" rowspan="2">
<table style="border-collapse:collapse;width:110px;color:#99a;font-family:'Helvetica','Lucida Grande','Arial',sans-serif;"><tbody>
- <tr>
- <td style="padding-right:9px;text-align:right;">
+
+ <!-- NEXT/PREV MONTH NAV AND MONTH INDICATOR -->
+ <tr style="width:110px;height:16px;font-size:10px!important;">
+ <td style="padding-right:9px;font-size:11px!important;font-weight: bold;text-align:right;white-space:nowrap;overflow:visible;" nowrap="nowrap">
<%
- if(data.prevResult == null) {
+ if(data.monthPrevResult == null) {
%>
- <img src="<%= staticPrefix %>images/toolbar/wm_tb_prv_on.png" alt="Previous capture" width="14" height="16" border="0" />
+ <%= fmt.format("ToolBar.noPrevMonthText",ToolBarData.addMonth(data.curResult.getCaptureDate(),-1)) %>
<%
} else {
%>
- <a href="<%= data.makeReplayURL(data.prevResult) %>" title="<%= fmt.format("ToolBar.prevTitle",data.prevResult.getCaptureDate()) %>"><img src="<%= staticPrefix %>images/toolbar/wm_tb_prv_on.png" alt="Previous capture" width="14" height="16" border="0" /></a>
+ <a href="<%= data.makeReplayURL(data.monthPrevResult) %>" style="text-decoration:none;color:#33f;" title="<%= fmt.format("ToolBar.prevMonthTitle",data.monthPrevResult.getCaptureDate()) %>"><%= fmt.format("ToolBar.prevMonthText",data.monthPrevResult.getCaptureDate()).toUpperCase() %></a>
<%
}
%>
</td>
- <td id="displayDayEl" style="background:#000;color:#ff0;width:34px;height:24px;padding:2px 0 0 0;text-align:center;font-size:22px;" title="<%= fmt.format("ToolBar.curDayTitle",data.curResult.getCaptureDate()) %>"><%= fmt.format("ToolBar.curDayText",data.curResult.getCaptureDate()) %></td>
- <td style="padding-left:9px;white-space:nowrap;overflow:visible;" nowrap="nowrap">
+ <td id="displayMonthEl" style="background:#000;color:#ff0;font-size:11px!important;font-weight: bold;width:34px;height:15px;padding-top:1px;text-align:center;" title="<%= fmt.format("ToolBar.curMonthTitle",data.curResult.getCaptureDate()) %>"><%= fmt.format("ToolBar.curMonthText",data.curResult.getCaptureDate()).toUpperCase() %></td>
+ <td style="padding-left:9px;font-size:11px!important;font-weight: bold;white-space:nowrap;overflow:visible;" nowrap="nowrap">
<%
- if(data.nextResult == null) {
+ if(data.monthNextResult == null) {
%>
- <img src="<%= staticPrefix %>images/toolbar/wm_tb_nxt_on.png" alt="Next capture" width="14" height="16" border="0"/>
+ <%= fmt.format("ToolBar.noNextMonthText",ToolBarData.addMonth(data.curResult.getCaptureDate(),1)) %>
<%
} else {
%>
- <a href="<%= data.makeReplayURL(data.nextResult) %>" title="<%= fmt.format("ToolBar.nextTitle",data.nextResult.getCaptureDate()) %>"><img src="<%= staticPrefix %>images/toolbar/wm_tb_nxt_on.png" alt="Next capture" width="14" height="16" border="0"/></a>
+ <a href="<%= data.makeReplayURL(data.monthNextResult) %>" style="text-decoration:none;color:#33f;" title="<%= fmt.format("ToolBar.nextMonthTitle",data.monthNextResult.getCaptureDate()) %>"><%= fmt.format("ToolBar.nextMonthText",data.monthNextResult.getCaptureDate()).toUpperCase() %></a>
<%
}
%>
- </td>
+ </td>
</tr>
- <tr style="width:110px;height:16px;font-size:10px!important;">
- <td style="padding-right:9px;text-align:right;white-space:nowrap;overflow:visible;" nowrap="nowrap">
+
+ <!-- NEXT/PREV CAPTURE NAV AND DAY OF MONTH INDICATOR -->
+ <tr>
+ <td style="padding-right:9px;text-align:right;">
<%
- if(data.monthPrevResult == null) {
+ if(data.prevResult == null) {
%>
- <%= fmt.format("ToolBar.noPrevMonthText",ToolBarData.addMonth(data.curResult.getCaptureDate(),-1)) %>
+ <img src="<%= staticPrefix %>images/toolbar/wm_tb_prv_on.png" alt="Previous capture" width="14" height="16" border="0" />
<%
} else {
%>
- <a href="<%= data.makeReplayURL(data.monthPrevResult) %>" style="text-decoration:none;color:#33f;" title="<%= fmt.format("ToolBar.prevMonthTitle",data.monthPrevResult.getCaptureDate()) %>"><%= fmt.format("ToolBar.prevMonthText",data.monthPrevResult.getCaptureDate()) %></a>
+ <a href="<%= data.makeReplayURL(data.prevResult) %>" title="<%= fmt.format("ToolBar.prevTitle",data.prevResult.getCaptureDate()) %>"><img src="<%= staticPrefix %>images/toolbar/wm_tb_prv_on.png" alt="Previous capture" width="14" height="16" border="0" /></a>
<%
}
%>
</td>
- <td id="displayMonthEl" style="background:#000;color:#ff0;font-size:12px!important;width:34px;height:15px;padding-top:1px;text-align:center;" title="<%= fmt.format("ToolBar.curMonthTitle",data.curResult.getCaptureDate()) %>"><%= fmt.format("ToolBar.curMonthText",data.curResult.getCaptureDate()) %></td>
+ <td id="displayDayEl" style="background:#000;color:#ff0;width:34px;height:24px;padding:2px 0 0 0;text-align:center;font-size:24px;font-weight: bold;" title="<%= fmt.format("ToolBar.curDayTitle",data.curResult.getCaptureDate()) %>"><%= fmt.format("ToolBar.curDayText",data.curResult.getCaptureDate()) %></td>
<td style="padding-left:9px;white-space:nowrap;overflow:visible;" nowrap="nowrap">
<%
- if(data.monthNextResult == null) {
+ if(data.nextResult == null) {
%>
- <%= fmt.format("ToolBar.noNextMonthText",ToolBarData.addMonth(data.curResult.getCaptureDate(),1)) %>
+ <img src="<%= staticPrefix %>images/toolbar/wm_tb_nxt_on.png" alt="Next capture" width="14" height="16" border="0"/>
<%
} else {
%>
- <a href="<%= data.makeReplayURL(data.monthNextResult) %>" style="text-decoration:none;color:#33f;" title="<%= fmt.format("ToolBar.nextMonthTitle",data.monthNextResult.getCaptureDate()) %>"><%= fmt.format("ToolBar.nextMonthText",data.monthNextResult.getCaptureDate()) %></a>
+ <a href="<%= data.makeReplayURL(data.nextResult) %>" title="<%= fmt.format("ToolBar.nextTitle",data.nextResult.getCaptureDate()) %>"><img src="<%= staticPrefix %>images/toolbar/wm_tb_nxt_on.png" alt="Next capture" width="14" height="16" border="0"/></a>
<%
}
%>
- </td>
+ </td>
</tr>
+ <!-- NEXT/PREV YEAR NAV AND YEAR INDICATOR -->
<tr style="width:110px;height:13px;font-size:9px!important;">
- <td style="padding-right:9px;text-align:right;white-space:nowrap;overflow:visible;" nowrap="nowrap">
+ <td style="padding-right:9px;font-size:11px!important;font-weight: bold;text-align:right;white-space:nowrap;overflow:visible;" nowrap="nowrap">
<%
if(data.yearPrevResult == null) {
%>
@@ -251,8 +256,8 @@
}
%>
</td>
- <td id="displayYearEl" style="background:#000;color:#ff0;font-size:10px!important;padding-top:1px;width:34px;height:13px;text-align:center;" title="<%= fmt.format("ToolBar.curYearTitle",data.curResult.getCaptureDate()) %>"><%= fmt.format("ToolBar.curYearText",data.curResult.getCaptureDate()) %></td>
- <td style="padding-left:9px;white-space:nowrap;overflow:visible;" nowrap="nowrap">
+ <td id="displayYearEl" style="background:#000;color:#ff0;font-size:11px!important;font-weight: bold;padding-top:1px;width:34px;height:13px;text-align:center;" title="<%= fmt.format("ToolBar.curYearTitle",data.curResult.getCaptureDate()) %>"><%= fmt.format("ToolBar.curYearText",data.curResult.getCaptureDate()) %></td>
+ <td style="padding-left:9px;font-size:11px!important;font-weight: bold;white-space:nowrap;overflow:visible;" nowrap="nowrap">
<%
if(data.yearNextResult == null) {
%>
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bra...@us...> - 2010-06-18 00:39:59
|
Revision: 3157
http://archive-access.svn.sourceforge.net/archive-access/?rev=3157&view=rev
Author: bradtofel
Date: 2010-06-18 00:39:52 +0000 (Fri, 18 Jun 2010)
Log Message:
-----------
INITIAL REV: new Query Replay .jsp which shows 1 year at a time, displaying the results on a 'cal' style calendar
Added Paths:
-----------
trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/query/BubbleCalendar.jsp
Added: trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/query/BubbleCalendar.jsp
===================================================================
--- trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/query/BubbleCalendar.jsp (rev 0)
+++ trunk/archive-access/projects/wayback/wayback-webapp/src/main/webapp/WEB-INF/query/BubbleCalendar.jsp 2010-06-18 00:39:52 UTC (rev 3157)
@@ -0,0 +1,604 @@
+<%@ page language="java" pageEncoding="utf-8" contentType="text/html;charset=utf-8"%>
+<%@ page import="java.util.List" %>
+<%@ page import="java.util.ArrayList" %>
+<%@ page import="java.util.Calendar" %>
+<%@ page import="java.util.Date" %>
+<%@ page import="java.util.Iterator" %>
+<%@ page import="org.archive.wayback.ResultURIConverter" %>
+<%@ page import="org.archive.wayback.WaybackConstants" %>
+<%@ page import="org.archive.wayback.core.CaptureSearchResult" %>
+<%@ page import="org.archive.wayback.core.CaptureSearchResults" %>
+<%@ page import="org.archive.wayback.core.UIResults" %>
+<%@ page import="org.archive.wayback.partition.BubbleCalendarData" %>
+<%@ page import="org.archive.wayback.util.partition.Partition" %>
+<%@ page import="org.archive.wayback.util.StringFormatter" %>
+<jsp:include page="/WEB-INF/template/CookieJS.jsp" flush="true" />
+<%
+UIResults results = UIResults.extractCaptureQuery(request);
+
+StringFormatter fmt = results.getWbRequest().getFormatter();
+ResultURIConverter uriConverter = results.getURIConverter();
+
+// deployment-specific URL prefixes
+String staticPrefix = results.getStaticPrefix();
+String queryPrefix = results.getQueryPrefix();
+String replayPrefix = results.getReplayPrefix();
+
+//deployment-specific address for the graph generator:
+String graphJspPrefix = results.getContextConfig("graphJspPrefix");
+if(graphJspPrefix == null) {
+ graphJspPrefix = queryPrefix;
+}
+
+// graph size "constants": These are currently baked-in to the JS logic...
+int imgWidth = 735;
+int imgHeight = 75;
+int yearWidth = 49;
+int monthWidth = 4;
+
+BubbleCalendarData data = new BubbleCalendarData(results);
+
+String yearEncoded = data.getYearsGraphString(imgWidth,imgHeight);
+String yearImgUrl = graphJspPrefix + "jsp/graph.jsp?graphdata=" + yearEncoded;
+
+// a Calendar object for doing days-in-week, day-of-week,days-in-month math:
+Calendar cal = BubbleCalendarData.getUTCCalendar();
+
+%>
+<script src="http://ajax.googleapis.com/ajax/libs/jquery/1.4.2/jquery.min.js" type="text/javascript"></script>
+<script src="http://ajax.googleapis.com/ajax/libs/jqueryui/1.8.1/jquery-ui.min.js" type="text/javascript"></script>
+<script type="text/javascript" src="<%= staticPrefix %>js/excanvas.compiled.js"></script>
+<script type="text/javascript" src="<%= staticPrefix %>js/jquery.bt.min.js" charset="utf-8"></script>
+<script type="text/javascript" src="<%= staticPrefix %>js/jquery.hoverintent.min.js" charset="utf-8"></script>
+<script type="text/javascript" src="<%= staticPrefix %>js/graph-calc.js" ></script>
+<!-- More ugly JS to manage the highlight over the graph -->
+<script type="text/javascript">
+
+
+var firstDate = <%= data.dataStartMSSE %>;
+var lastDate = <%= data.dataEndMSSE %>;
+var wbPrefix = "<%= replayPrefix %>";
+var wbCurrentUrl = "<%= data.searchUrlForJS %>";
+
+var curYear = <%= data.yearNum - 1996 %>;
+var curMonth = -1;
+var yearCount = 15;
+var firstYear = 1996;
+var startYear = <%= data.yearNum - 1996 %>;
+var imgWidth = <%= imgWidth %>;
+var yearImgWidth = <%= yearWidth %>;
+var monthImgWidth = <%= monthWidth %>;
+var trackerVal = "none";
+
+function showTrackers(val) {
+ if(val == trackerVal) {
+ return;
+ }
+
+ document.getElementById("wbMouseTrackYearImg").style.display = val;
+ trackerVal = val;
+}
+function getElementX2(obj) {
+ var thing = jQuery(obj);
+ if((thing == undefined)
+ || (typeof thing == "undefined")
+ || (typeof thing.offset == "undefined")) {
+ return getElementX(obj);
+ }
+ return Math.round(thing.offset().left);
+}
+function setActiveYear(year) {
+ if(curYear != year) {
+ var yrOff = year * yearImgWidth;
+ document.getElementById("wbMouseTrackYearImg").style.left = yrOff + "px";
+ if(curYear != -1) {
+ document.getElementById("highlight-"+curYear).setAttribute("class","inactiveHighlight");
+ }
+ document.getElementById("highlight-"+year).setAttribute("class","activeHighlight");
+ curYear = year;
+ }
+}
+function trackMouseMove(event,element) {
+
+ var eventX = getEventX(event);
+ var elementX = getElementX2(element);
+ var xOff = eventX - elementX;
+ if(xOff < 0) {
+ xOff = 0;
+ } else if(xOff > imgWidth) {
+ xOff = imgWidth;
+ }
+ var monthOff = xOff % yearImgWidth;
+
+ var year = Math.floor(xOff / yearImgWidth);
+ var yearStart = year * yearImgWidth;
+ var monthOfYear = Math.floor(monthOff / monthImgWidth);
+ if(monthOfYear > 11) {
+ monthOfYear = 11;
+ }
+ var month = (year * 12) + monthOfYear;
+ var day = 1;
+ if(monthOff % 2 == 1) {
+ day = 15;
+ }
+ var dateString =
+ zeroPad(year + firstYear) +
+ zeroPad(monthOfYear+1,2) +
+ zeroPad(day,2) + "000000";
+
+ var url = wbPrefix + dateString + '*/' + wbCurrentUrl;
+ document.getElementById('wm-graph-anchor').href = url;
+ setActiveYear(year);
+}
+</script>
+
+<script type="text/javascript">
+$().ready(function(){
+ $(".date").each(function(i){
+ var size = $(this).find(".hidden").text();
+ var offset = size / 2;
+ if (size >= 1 && size <= 20) {size = 20, offset = 10;}
+ $(this).find("img").attr("src","<%= staticPrefix %>images/blueblob-dk.png");
+ $(this).find(".measure").css({'width':+size+'px','height':+size+'px','top':'-'+offset+'px','left':'-'+offset+'px'});
+ });
+ $(".day a").each(function(i){
+ var dateClass = $(this).attr("class");
+ var dateId = "#"+dateClass;
+ $(this).hover(function(){
+ $(dateId).removeClass("opacity20");
+ },function(){
+ $(dateId).addClass("opacity20");
+ });
+ });
+ $(".tooltip").bt({
+ positions: ['top','right','left','bottom'],
+ contentSelector: "$(this).find('.pop').html()",
+ padding: '0',
+ width: '145px',
+ spikeGirth: 12,
+ spikeLength: 12,
+ overlap: '2px',
+ cornerRadius: 5,
+ fill: '#efefef',
+ strokeWidth: 1,
+ strokeStyle: '#efefef',
+ shadow: true,
+ shadowColor: '#333',
+ shadowBlur: 6,
+ shadowOffsetX: 0,
+ shadowOffsetY: 0,
+ noShadowOpts: {strokeStyle:'#ccc'},
+ hoverIntentOpts: {interval:0,timeout:4000},
+ clickAnywhereToClose: true,
+ closeWhenOthersOpen: true,
+ windowMargin: 30,
+ cssStyles: {
+ fontSize: '12px',
+ fontFamily: '"Arial","Helvetica Neue","Helvetica",sans-serif',
+ lineHeight: 'normal',
+ padding: '10px',
+ color: '#333'
+ }
+ });
+});
+</script>
+<style type="text/css">
+body,div,p,td,th,ul,ol,li {margin:0;padding:0;}
+body {background-color:#fff;font-family:"Arial","Helvetica Neue","Helvetica",sans-serif;font-size:100%;}
+img {border:none;}
+a {color:#069;}
+.clearfix{width:100%;clear:both;}
+.clearfix:after {content:".";display:block;height:0;clear:both;visibility:hidden;}
+#position {padding:0;margin:0 auto;width:990px;background-color:#fff;}
+#wbCalendar {position:relative;width:990px;margin-top:25px;}
+.calPosition {padding:15px 0 25px 25px;}
+#calUnder {overflow:hidden;}
+#calOver {position:absolute;top:0;left:0;}
+.hidden{display:none;}
+.opacity20 {
+ opacity:.2;
+ -ms-filter:"progid:DXImageTransform.Microsoft.Alpha(Opacity=20)";
+ filter: alpha(opacity=20);
+}
+.month {
+ width: 240px;
+ height: 210px;
+ float: left;
+}
+.month table {
+ border-collapse: collapse;
+ font-family: "Arial", sans-serif;
+ border-spacing: 1px;
+}
+.month table th {
+ font-size: 0.75em;
+ font-weight: 700;
+ text-transform: uppercase;
+ padding: 6px;
+}
+.month table span.label {
+ display: block;
+ min-height: 20px;
+}
+.month table td {
+ padding: 0;
+ vertical-align: middle;
+ color: #666;
+}
+.month table td .day {
+ width: 30px;
+ height: 30px;
+ text-align: center;
+}
+.month table td .day a,
+.month table td .day span {
+ display: block;
+ font-size: 0.6875em;
+ width: 30px;
+ height: 22px;
+ padding-top: 8px;
+}
+.month table td .day a {
+ color: #000;
+ font-weight: 700;
+ text-decoration: none;
+}
+.month table td .day span {
+ padding-top: 9px;
+ height: 19px;
+}
+.month table td .day a:hover {
+ font-size: 0.9375em;
+ padding-top: 6px;
+ height: 22px;
+}
+.month table td .date {
+ width: 30px;
+ height: 30px;
+}
+.month table td .position {
+ position: relative;
+ top: 15px;
+ left: 15px;
+ width: 1px;
+ height: 1px;
+}
+.month table td .measure {
+ position: absolute;
+}
+.activeHighlight {
+ background-color: #000!important;
+ padding-top: 4px;
+ font-size: 1.375em!important;
+ color: #fff300!important;
+ font-weight: normal!important;
+ cursor: pointer;
+}
+.inactiveHighlight {
+ background-color: #fff!important;
+ padding-top: 4px;
+ font-size: .75em!important;
+ color: #000!important;
+ font-weight: normal!important;
+ cursor: pointer;
+}
+
+.bt-content {
+ text-align: left;
+}
+.pop {display:none;}
+.bt-content h3 {font-size: 1em;font-weight: 700;text-transform: uppercase;margin:0 0 5px;}
+.bt-content p {font-size: 0.875em;margin: 5px 0;color:#666;}
+.bt-content ul {line-height:1.5em;margin:0 0 0 1em;}
+.bt-content em {color:#999;}
+.bt-content a:hover {color:#036;}
+
+#wbSearch {float:left;padding:30px 30px 0;}
+#wbSearch #logo {float:left; width:223px;}
+#wbSearch #form {float:left;width:707px;}
+#wbSearch form {margin:0;padding:0;}
+#wbSearch input {font-family:"Arial","Helvetica Neue","Helvetica",sans-serif;font-size:1.125em;}
+#wbSearch input[type=text] {width:450px;font-weight:700;}
+#wbSearch input[type=submit] {vertical-align: middle;}
+#wbMeta {padding:15px 0;}
+#wbMeta p {margin:0 0 2px;padding:0;}
+#wbMeta p.wbThis {font-size:0.75em;}
+#wbMeta p.wbNote {color:#666;font-size: 0.6875em;}
+#wbMeta p.wbNote a {color:#666;}
+#wbChart {text-align:center;padding:0 30px;}
+#wbChartThis {position:relative;margin:0 auto;}
+.wbChartThisContainer,.wbChartHover {width:<%= yearWidth %>px;height:30px;float:left;overflow:visible;}
+.wbChartThisTop {
+ width: <%= yearWidth %>px;
+ height: 80px;
+ border: 1px solid #ccc;
+}
+.wbGradient {
+ background: #f3f3f3 -moz-linear-gradient(top,#ffffff,#f3f3f3);
+ background: #f3f3f3 -webkit-gradient(linear, left top, left bottom, from(#fff), to(#f3f3f3), color-stop(1.0, #f3f3f3));
+ background-color: #f3f3f3;
+ filter: progid:DXImageTransform.Microsoft.Gradient(enabled='true',startColorstr=#FFFFFFFF, endColorstr=#FFF3F3F3);
+}
+.wbSelected, #wbSelected {
+ background: #fff300!important;
+ border-bottom: 1px solid #000!important;
+ filter: progid:DXImageTransform.Microsoft.Gradient(enabled='false')!important;
+ cursor: pointer;
+}
+#wbSelected {
+ cursor: default!important;
+}
+.wbChartThisBtm {
+ text-align:center;
+}
+.wbChartSm {
+ padding-top: 4px;
+ font-size: 0.625em;
+ color: #999;
+ font-weight: 700;
+}
+.wbChartBig, #wbChartBig {
+ background-color: #000!important;
+ padding-top: 4px;
+ font-size: 1.375em!important;
+ color: #fff300!important;
+ font-weight: normal!important;
+ cursor: pointer;
+}
+#wbChartBig {
+ cursor: default!important;
+}
+#wbChartGraph,#wbChartOver {
+ position: absolute;
+ top: 1px;
+ left: 1px;
+ cursor: pointer;
+}
+
+</style>
+
+<script type="text/javascript">
+$().ready(function(){
+ var yrCount = $(".wbChartThisContainer").size();
+ var yrTotal = <%= yearWidth %> * yrCount;
+ var yrPad = (930 - yrTotal) / 2;
+ $("#wbChartThis").css("padding-left",yrPad+"px");
+});
+</script>
+
+<div id="wbChart">
+
+ <div id="wbChartThis">
+ <a style="position:relative; white-space:nowrap; width:<%= imgWidth %>px;height:<%= imgHeight %>px;" href="" id="wm-graph-anchor">
+ <div id="wm-ipp-sparkline" style="position:relative; white-space:nowrap; width:<%= imgWidth %>px;height:<%= imgHeight %>px;background: #f3f3f3 -moz-linear-gradient(top,#ffffff,#f3f3f3);background: #f3f3f3 -webkit-gradient(linear, left top, left bottom, from(#fff), to(#f3f3f3), color-stop(1.0, #f3f3f3));background-color: #f3f3f3;filter: progid:DXImageTransform.Microsoft.Gradient(enabled='true',startColorstr=#FFFFFFFF, endColorstr=#FFF3F3F3);cursor:pointer;border: 1px solid #ccc;border-left:none;" title="<%= fmt.format("ToolBar.sparklineTitle") %>">
+ <img id="sparklineImgId" style="position:absolute;z-index:9012;top:0;left:0;"
+ onmouseover="showTrackers('inline');"
+ onmouseout="showTrackers('none');"
+ onmousemove="trackMouseMove(event,this)"
+ alt="sparklines"
+ width="<%= imgWidth %>"
+ height="<%= imgHeight %>"
+ border="0"
+ src="<%= yearImgUrl %>"></img>
+ <img id="wbMouseTrackYearImg"
+ style="display:none; position:absolute; z-index:9010;"
+ width="<%= yearWidth %>"
+ height="<%= imgHeight %>"
+ border="0"
+ src="<%= staticPrefix %>images/toolbar/transp-yellow-pixel.png"></img>
+ <img id="wbMouseTrackMonthImg"
+ style="display:none; position:absolute; z-index:9011; "
+ width="<%= monthWidth %>"
+ height="<%= imgHeight %>"
+ border="0"
+ src="<%= staticPrefix %>images/toolbar/transp-red-pixel.png"></img>
+ </div>
+ </a>
+ <%
+ for(int i = 1996; i < 2011; i++) {
+ String curClass = "inactiveHighlight";
+ if(data.yearNum == i) {
+ curClass = "activeHighlight";
+ }
+ %>
+ <div class="wbChartThisContainer">
+ <a style="text-decoration: none;" href="<%= queryPrefix + i + "0101000000*/" + data.searchUrlForJS %>">
+
+ <div id="highlight-<%= i - 1996 %>"
+ onmouseover="showTrackers('inline'); setActiveYear(<%= i - 1996 %>)"
+ onmouseout="showTrackers('none');"
+ class="<%= curClass %>"><%= i %></div>
+ </a>
+ </div>
+ <%
+ }
+ %>
+ </div>
+</div>
+<div class="clearfix"></div>
+
+<div id="wbCalendar">
+
+ <div id="calUnder" class="calPosition">
+
+
+
+
+<%
+// draw 12 months, 0-11 (0=Jan, 11=Dec)
+for(int moy = 0; moy < 12; moy++) {
+ Partition<Partition<CaptureSearchResult>> curMonth = data.monthsByDay.get(moy);
+ List<Partition<CaptureSearchResult>> monthDays = curMonth.list();
+%>
+ <div class="month" id="<%= data.yearNum %>-<%= moy %>">
+ <table>
+
+ <thead>
+ <tr>
+ <th colspan="7"><span class="label"></span></th>
+ </tr>
+ </thead>
+ <tbody>
+ <tr>
+<%
+ cal.setTime(curMonth.getStart());
+ int skipDays = cal.get(Calendar.DAY_OF_WEEK) - 1;
+ int daysInMonth = cal.getActualMaximum(Calendar.DAY_OF_MONTH);
+ // skip until the 1st:
+ for(int i = 0; i < skipDays; i++) {
+ %><td><div class="date"></div></td><%
+ }
+ int dow = skipDays;
+ int dom;
+ for(dom = 0; dom < daysInMonth; dom++) {
+
+
+ int count = monthDays.get(dom).count();
+ if(count > 0) {
+ // one or more captures in this day:
+ CaptureSearchResult firstCaptureInDay =
+ monthDays.get(dom).list().get(0);
+ String replayUrl = uriConverter.makeReplayURI(
+ firstCaptureInDay.getCaptureTimestamp(),
+ firstCaptureInDay.getOriginalUrl());
+ String safeUrl = fmt.escapeHtml(replayUrl);
+ %><td>
+ <div class="date">
+ <div class="position">
+ <div class="hidden"><%= count %></div>
+ <div class="measure opacity20" id=""><img width="100%" height="100%"/></div>
+ </div>
+ </div>
+ </td><%
+
+ } else {
+ // zero captures in this day:
+ %><td>
+ <div class="date"></div>
+ </td><%
+
+ }
+
+
+ if(((dom+skipDays+1) % 7) == 0) {
+ // end of the week, start a new tr:
+ %></tr><tr><%
+ }
+ }
+ // fill in blank days until the end of the current week:
+ while(((dom+skipDays) % 7) != 0) {
+ %><td></td><%
+ dom++;
+ }
+%>
+ </tr>
+ </tbody>
+ </table>
+ </div>
+
+<%
+}
+%>
+ </div>
+ <div id="calOver" class="calPosition">
+<%
+
+for(int moy = 0; moy < 12; moy++) {
+ Partition<Partition<CaptureSearchResult>> curMonth = data.monthsByDay.get(moy);
+ List<Partition<CaptureSearchResult>> monthDays = curMonth.list();
+%>
+ <div class="month" id="<%= data.yearNum %>-<%= moy %>">
+ <table>
+
+ <thead>
+ <tr>
+ <th colspan="7"><span class="label"><%= fmt.format("{0,date,MMM}",curMonth.getStart()) %></span></th>
+ </tr>
+ </thead>
+ <tbody>
+ <tr>
+<%
+ cal.setTime(curMonth.getStart());
+ int skipDays = cal.get(Calendar.DAY_OF_WEEK) - 1;
+ int daysInMonth = cal.getActualMaximum(Calendar.DAY_OF_MONTH);
+ // skip until the 1st:
+ for(int i = 0; i < skipDays; i++) {
+ %><td><div class="date"></div></td><%
+ }
+ int dow = skipDays;
+ int dom;
+ for(dom = 0; dom < daysInMonth; dom++) {
+
+
+ int count = monthDays.get(dom).count();
+
+ if(count > 0) {
+ // one or more captures in this day:
+ CaptureSearchResult firstCaptureInDay =
+ monthDays.get(dom).list().get(0);
+ String replayUrl = uriConverter.makeReplayURI(
+ firstCaptureInDay.getCaptureTimestamp(),
+ firstCaptureInDay.getOriginalUrl());
+ Date firstCaptureInDayDate = firstCaptureInDay.getCaptureDate();
+ String safeUrl = fmt.escapeHtml(replayUrl);
+ int dupes = 999;
+
+ %><td>
+ <div class="date tooltip">
+ <div class="pop">
+ <h3><%= fmt.format("{0,date,MMMMM d, yyyy}",firstCaptureInDayDate) %></h3>
+ <p><%= count %> snapshots, <em><%= dupes %> duplicates</em></p>
+ <ul>
+ <%
+ Iterator<CaptureSearchResult> dayItr =
+ monthDays.get(dom).iterator();
+ while(dayItr.hasNext()) {
+ CaptureSearchResult c = dayItr.next();
+ String replayUrl2 = uriConverter.makeReplayURI(
+ c.getCaptureTimestamp(),c.getOriginalUrl());
+ String safeUrl2 = fmt.escapeHtml(replayUrl2);
+ %>
+ <li><a href="<%= safeUrl2 %>"><%= fmt.format("{0,date,HH:mm:ss}",c.getCaptureDate()) %></a></li>
+ <%
+ }
+ %>
+ </ul>
+ </div>
+ <div class="day">
+
+ <a href="<%= safeUrl %>" title="<%= count %> snapshots (<%= dupes %> duplicates)" class="<%= fmt.format("{0,date,MMM-d-yyyy}",firstCaptureInDayDate) %>"><%= dom + 1 %></a>
+ </div>
+ </div>
+ </td><%
+
+ } else {
+ // zero captures in this day:
+ %><td>
+ <div class="date">
+ <div class="day"><span><%= dom + 1 %></span></div>
+ </div>
+ </td><%
+
+ }
+
+
+ if(((dom+skipDays+1) % 7) == 0) {
+ // end of the week, start a new tr:
+ %></tr><tr><%
+ }
+ }
+ // fill in blank days until the end of the current week:
+ while(((dom+skipDays) % 7) != 0) {
+ %><td></td><%
+ dom++;
+ }
+%>
+ </tr>
+ </tbody>
+ </table>
+ </div>
+<%
+}
+%>
+ </div>
+ </div>
\ No newline at end of file
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bra...@us...> - 2010-06-18 00:39:02
|
Revision: 3156
http://archive-access.svn.sourceforge.net/archive-access/?rev=3156&view=rev
Author: bradtofel
Date: 2010-06-18 00:38:56 +0000 (Fri, 18 Jun 2010)
Log Message:
-----------
made wrapperJsp optional... duh.
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/webapp/AccessPoint.java
Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/webapp/AccessPoint.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/webapp/AccessPoint.java 2010-06-14 19:17:21 UTC (rev 3155)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/webapp/AccessPoint.java 2010-06-18 00:38:56 UTC (rev 3156)
@@ -105,7 +105,8 @@
private String queryPrefix = null;
private String replayPrefix = null;
- private String wrapperJsp = "/WEB-INF/template/UI-wrapper.jsp";
+// private String wrapperJsp = "/WEB-INF/template/UI-wrapper.jsp";
+ private String wrapperJsp = null;
private String interstitialJsp = INTERSTITIAL_JSP;
private String refererAuth = null;
@@ -148,7 +149,9 @@
wbRequest.fixup(httpRequest);
UIResults uiResults = new UIResults(wbRequest,uriConverter);
try {
- if(translatedNoQuery.endsWith("-wrap.jsp")) {
+ if(wrapperJsp != null &&
+ translatedNoQuery.endsWith("-wrap.jsp")) {
+
uiResults.forwardWrapped(httpRequest, httpResponse,
translatedQ, wrapperJsp);
} else {
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
