From c7576d60286ae25a26c651de14343122b9836882 Mon Sep 17 00:00:00 2001
From: Michael Peter Christen <mc@yacy.net>
Date: Fri, 29 May 2015 15:05:52 +0200
Subject: added a full solr export to the IndexControlURLs_p.html servlet. The
 export function is also now the default export option. The export file format
 for a full solr export is very similar to a solr search result xml, only the
 <lst name="responseHeader"> tag is missing.

The exported xml has a special line termination feature: all documents
will be exported into a single line without any CR in between. That
means that every document is completely inside a single line. While this
is not readable at all for humans, it is very useful for linux line
processing scripts, like grep. Using grep it will be easy to select
single documents which match for a given pattern.

Such dumps shall be importable with the DATA/SURROGATE/in import
function, but that import is not yet adopted to the new file format.
---
 htroot/IndexControlURLs_p.html | 33 ++++++++++++++++++---------------
 1 file changed, 18 insertions(+), 15 deletions(-)

(limited to 'htroot/IndexControlURLs_p.html')

diff --git a/htroot/IndexControlURLs_p.html b/htroot/IndexControlURLs_p.html
index e4eee30f5..0d245a6ab 100644
--- a/htroot/IndexControlURLs_p.html
+++ b/htroot/IndexControlURLs_p.html
@@ -118,7 +118,7 @@ function updatepage(str) {
     <form action="IndexControlURLs_p.html" method="post" enctype="multipart/form-data" accept-charset="UTF-8">
     <fieldset><legend>Statistics about top-domains in URL Database</legend>
       <dl>
-        <dt class="TableCellDark">&nbsp;</dt>
+        <dt>&nbsp;</dt>
         <dd>Show top <input type="text" name="lines" value="#[lines]#" size="6" maxlength="6" /> domains from all URLs.
             <input type="submit" name="statistics" value="Generate Statistics" class="btn btn-primary" style="width:240px;"/>
         </dd>
@@ -157,7 +157,7 @@ function updatepage(str) {
     <form action="IndexControlURLs_p.html" method="post" enctype="multipart/form-data" accept-charset="UTF-8">
     <fieldset><legend>Dump and Restore of Solr Index</legend>
       <dl>
-        <dt class="TableCellDark">&nbsp;</dt>
+        <dt>&nbsp;</dt>
         <dd><input type="submit" name="indexdump" value="Create Dump" class="btn btn-primary" style="width:240px;"/>
         </dd>
       </dl>
@@ -165,7 +165,7 @@ function updatepage(str) {
         <dt class="TableCellDark">Dump File</dt>
         <dd><input type="text" name="dumpfile" value="#[dumpfile]#" size="80" maxlength="250" />
         </dd>
-        <dt class="TableCellDark">&nbsp;</dt>
+        <dt>&nbsp;</dt>
         <dd><input type="submit" name="indexrestore" value="Restore Dump" class="btn btn-primary" style="width:240px;"/>
         </dd>
       </dl>
@@ -174,7 +174,7 @@ function updatepage(str) {
     <form action="IndexControlURLs_p.html" method="post" enctype="multipart/form-data" accept-charset="UTF-8">
     <fieldset><legend>Optimize Solr</legend>
       <dl>
-        <dt class="TableCellDark">&nbsp;</dt>
+        <dt>&nbsp;</dt>
         <dd>merge to max. <input type="text" name="optimizemax" value="#[optimizemax]#" size="6" maxlength="6" /> segments
         <input type="submit" name="optimizesolr" value="Optimize Solr" class="btn btn-primary" style="width:240px;"/>
         </dd>
@@ -184,7 +184,7 @@ function updatepage(str) {
     <form action="IndexControlURLs_p.html" method="post" enctype="multipart/form-data" accept-charset="UTF-8">
     <fieldset><legend>Reboot Solr Core</legend>
       <dl>
-        <dt class="TableCellDark">&nbsp;</dt>
+        <dt>&nbsp;</dt>
         <dd><input type="submit" name="rebootsolr" value="Shut Down and Re-Start Solr" class="btn btn-primary" style="width:240px;"/>
         </dd>
       </dl>
@@ -206,16 +206,19 @@ function updatepage(str) {
         <dd><input type="text" name="exportquery" value="*:*" size="20" maxlength="250" />
         </dd>
         <dt class="TableCellDark">Export Format</dt>
-        <dd>Only Domain:
-            <input type="radio" name="format" value="dom-text" />Plain Text List (domains only)&nbsp;&nbsp;
-            <input type="radio" name="format" value="dom-html" checked="checked" />HTML (domains as URLs, no title)<br />
-            Full URL List:
-            <input type="radio" name="format" value="url-text" />Plain Text List (URLs only)&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
-            <input type="radio" name="format" value="url-html" />HTML (URLs with title)&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
-            <input type="radio" name="format" value="url-rss" />XML (RSS)
-            <br />
-        </dd>
-        <dt class="TableCellDark">&nbsp;</dt>
+        <dd>
+        <dl>
+        <dt>Only Domain:</dt>
+        <dd><input type="radio" name="format" value="dom-text" /> Plain Text List (domains only)<br />
+            <input type="radio" name="format" value="dom-html" /> HTML (domains as URLs, no title)</dd>
+        <dt>Full URL List:</dt>
+        <dd><input type="radio" name="format" value="url-text" /> Plain Text List (URLs only)<br />
+            <input type="radio" name="format" value="url-html" /> HTML (URLs with title)</dd>
+        <dt>Full Data Records:</dt>
+        <dd><input type="radio" name="format" value="full-rss" /> XML (RSS)<br />
+            <input type="radio" name="format" value="full-solr" checked="checked" /> XML (Rich and full Solr data using Solr Schema, can be imported with DATA/SURROGATE/in/)</dd>
+		</dl></dd>
+        <dt>&nbsp;</dt>
         <dd><input type="submit" name="lurlexport" value="Export URLs" class="btn btn-primary" style="width:240px;"/>
         </dd>
       </dl>
-- 
cgit v1.2.3