<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:x="urn:schemas-microsoft-com:office:excel" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii">
<meta name="Generator" content="Microsoft Word 14 (filtered medium)">
<style><!--
/* Font Definitions */
@font-face
        {font-family:Wingdings;
        panose-1:5 0 0 0 0 0 0 0 0 0;}
@font-face
        {font-family:Wingdings;
        panose-1:5 0 0 0 0 0 0 0 0 0;}
@font-face
        {font-family:Calibri;
        panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
        {font-family:Tahoma;
        panose-1:2 11 6 4 3 5 4 4 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
        {margin:0in;
        margin-bottom:.0001pt;
        font-size:11.0pt;
        font-family:"Calibri","sans-serif";}
a:link, span.MsoHyperlink
        {mso-style-priority:99;
        color:#0563C1;
        text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
        {mso-style-priority:99;
        color:#954F72;
        text-decoration:underline;}
code
        {mso-style-priority:99;
        font-family:"Courier New";}
pre
        {mso-style-priority:99;
        mso-style-link:"HTML Preformatted Char";
        margin:0in;
        margin-bottom:.0001pt;
        font-size:10.0pt;
        font-family:"Courier New";}
p.MsoListParagraph, li.MsoListParagraph, div.MsoListParagraph
        {mso-style-priority:34;
        margin-top:0in;
        margin-right:0in;
        margin-bottom:0in;
        margin-left:.5in;
        margin-bottom:.0001pt;
        font-size:11.0pt;
        font-family:"Calibri","sans-serif";}
span.EmailStyle18
        {mso-style-type:personal;
        font-family:"Calibri","sans-serif";
        color:windowtext;}
span.EmailStyle19
        {mso-style-type:personal-reply;
        font-family:"Calibri","sans-serif";
        color:#1F497D;}
span.HTMLPreformattedChar
        {mso-style-name:"HTML Preformatted Char";
        mso-style-priority:99;
        mso-style-link:"HTML Preformatted";
        font-family:"Courier New";}
.MsoChpDefault
        {mso-style-type:export-only;
        font-size:10.0pt;}
@page WordSection1
        {size:8.5in 11.0in;
        margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
        {page:WordSection1;}
/* List Definitions */
@list l0
        {mso-list-id:417363316;
        mso-list-template-ids:1280074224;}
@list l0:level1
        {mso-level-number-format:bullet;
        mso-level-text:\F0B7;
        mso-level-tab-stop:.5in;
        mso-level-number-position:left;
        text-indent:-.25in;
        mso-ansi-font-size:10.0pt;
        font-family:Symbol;}
@list l0:level2
        {mso-level-number-format:bullet;
        mso-level-text:o;
        mso-level-tab-stop:1.0in;
        mso-level-number-position:left;
        text-indent:-.25in;
        mso-ansi-font-size:10.0pt;
        font-family:"Courier New";
        mso-bidi-font-family:"Times New Roman";}
@list l0:level3
        {mso-level-number-format:bullet;
        mso-level-text:\F0A7;
        mso-level-tab-stop:1.5in;
        mso-level-number-position:left;
        text-indent:-.25in;
        mso-ansi-font-size:10.0pt;
        font-family:Wingdings;}
@list l0:level4
        {mso-level-number-format:bullet;
        mso-level-text:\F0A7;
        mso-level-tab-stop:2.0in;
        mso-level-number-position:left;
        text-indent:-.25in;
        mso-ansi-font-size:10.0pt;
        font-family:Wingdings;}
@list l0:level5
        {mso-level-number-format:bullet;
        mso-level-text:\F0A7;
        mso-level-tab-stop:2.5in;
        mso-level-number-position:left;
        text-indent:-.25in;
        mso-ansi-font-size:10.0pt;
        font-family:Wingdings;}
@list l0:level6
        {mso-level-number-format:bullet;
        mso-level-text:\F0A7;
        mso-level-tab-stop:3.0in;
        mso-level-number-position:left;
        text-indent:-.25in;
        mso-ansi-font-size:10.0pt;
        font-family:Wingdings;}
@list l0:level7
        {mso-level-number-format:bullet;
        mso-level-text:\F0A7;
        mso-level-tab-stop:3.5in;
        mso-level-number-position:left;
        text-indent:-.25in;
        mso-ansi-font-size:10.0pt;
        font-family:Wingdings;}
@list l0:level8
        {mso-level-number-format:bullet;
        mso-level-text:\F0A7;
        mso-level-tab-stop:4.0in;
        mso-level-number-position:left;
        text-indent:-.25in;
        mso-ansi-font-size:10.0pt;
        font-family:Wingdings;}
@list l0:level9
        {mso-level-number-format:bullet;
        mso-level-text:\F0A7;
        mso-level-tab-stop:4.5in;
        mso-level-number-position:left;
        text-indent:-.25in;
        mso-ansi-font-size:10.0pt;
        font-family:Wingdings;}
@list l1
        {mso-list-id:668754871;
        mso-list-template-ids:1384681812;}
@list l1:level1
        {mso-level-tab-stop:.5in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l1:level2
        {mso-level-number-format:bullet;
        mso-level-text:o;
        mso-level-tab-stop:1.0in;
        mso-level-number-position:left;
        text-indent:-.25in;
        mso-ansi-font-size:10.0pt;
        font-family:"Courier New";
        mso-bidi-font-family:"Times New Roman";}
@list l1:level3
        {mso-level-tab-stop:1.5in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l1:level4
        {mso-level-tab-stop:2.0in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l1:level5
        {mso-level-tab-stop:2.5in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l1:level6
        {mso-level-tab-stop:3.0in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l1:level7
        {mso-level-tab-stop:3.5in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l1:level8
        {mso-level-tab-stop:4.0in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l1:level9
        {mso-level-tab-stop:4.5in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l2
        {mso-list-id:844825250;
        mso-list-template-ids:1951670282;}
@list l2:level1
        {mso-level-tab-stop:.5in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l2:level2
        {mso-level-number-format:bullet;
        mso-level-text:o;
        mso-level-tab-stop:1.0in;
        mso-level-number-position:left;
        text-indent:-.25in;
        mso-ansi-font-size:10.0pt;
        font-family:"Courier New";
        mso-bidi-font-family:"Times New Roman";}
@list l2:level3
        {mso-level-tab-stop:1.5in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l2:level4
        {mso-level-tab-stop:2.0in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l2:level5
        {mso-level-tab-stop:2.5in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l2:level6
        {mso-level-tab-stop:3.0in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l2:level7
        {mso-level-tab-stop:3.5in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l2:level8
        {mso-level-tab-stop:4.0in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l2:level9
        {mso-level-tab-stop:4.5in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l3
        {mso-list-id:982007541;
        mso-list-type:hybrid;
        mso-list-template-ids:911517712 67698705 67698713 67698715 67698703 67698713 67698715 67698703 67698713 67698715;}
@list l3:level1
        {mso-level-text:"%1\)";
        mso-level-tab-stop:none;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l3:level2
        {mso-level-number-format:alpha-lower;
        mso-level-tab-stop:none;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l3:level3
        {mso-level-number-format:roman-lower;
        mso-level-tab-stop:none;
        mso-level-number-position:right;
        text-indent:-9.0pt;}
@list l3:level4
        {mso-level-tab-stop:none;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l3:level5
        {mso-level-number-format:alpha-lower;
        mso-level-tab-stop:none;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l3:level6
        {mso-level-number-format:roman-lower;
        mso-level-tab-stop:none;
        mso-level-number-position:right;
        text-indent:-9.0pt;}
@list l3:level7
        {mso-level-tab-stop:none;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l3:level8
        {mso-level-number-format:alpha-lower;
        mso-level-tab-stop:none;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l3:level9
        {mso-level-number-format:roman-lower;
        mso-level-tab-stop:none;
        mso-level-number-position:right;
        text-indent:-9.0pt;}
@list l4
        {mso-list-id:1363899522;
        mso-list-template-ids:-792662430;}
@list l4:level1
        {mso-level-number-format:bullet;
        mso-level-text:\F0B7;
        mso-level-tab-stop:.5in;
        mso-level-number-position:left;
        text-indent:-.25in;
        mso-ansi-font-size:10.0pt;
        font-family:Symbol;}
@list l4:level2
        {mso-level-number-format:bullet;
        mso-level-text:o;
        mso-level-tab-stop:1.0in;
        mso-level-number-position:left;
        text-indent:-.25in;
        mso-ansi-font-size:10.0pt;
        font-family:"Courier New";
        mso-bidi-font-family:"Times New Roman";}
@list l4:level3
        {mso-level-number-format:bullet;
        mso-level-text:\F0A7;
        mso-level-tab-stop:1.5in;
        mso-level-number-position:left;
        text-indent:-.25in;
        mso-ansi-font-size:10.0pt;
        font-family:Wingdings;}
@list l4:level4
        {mso-level-number-format:bullet;
        mso-level-text:\F0A7;
        mso-level-tab-stop:2.0in;
        mso-level-number-position:left;
        text-indent:-.25in;
        mso-ansi-font-size:10.0pt;
        font-family:Wingdings;}
@list l4:level5
        {mso-level-number-format:bullet;
        mso-level-text:\F0A7;
        mso-level-tab-stop:2.5in;
        mso-level-number-position:left;
        text-indent:-.25in;
        mso-ansi-font-size:10.0pt;
        font-family:Wingdings;}
@list l4:level6
        {mso-level-number-format:bullet;
        mso-level-text:\F0A7;
        mso-level-tab-stop:3.0in;
        mso-level-number-position:left;
        text-indent:-.25in;
        mso-ansi-font-size:10.0pt;
        font-family:Wingdings;}
@list l4:level7
        {mso-level-number-format:bullet;
        mso-level-text:\F0A7;
        mso-level-tab-stop:3.5in;
        mso-level-number-position:left;
        text-indent:-.25in;
        mso-ansi-font-size:10.0pt;
        font-family:Wingdings;}
@list l4:level8
        {mso-level-number-format:bullet;
        mso-level-text:\F0A7;
        mso-level-tab-stop:4.0in;
        mso-level-number-position:left;
        text-indent:-.25in;
        mso-ansi-font-size:10.0pt;
        font-family:Wingdings;}
@list l4:level9
        {mso-level-number-format:bullet;
        mso-level-text:\F0A7;
        mso-level-tab-stop:4.5in;
        mso-level-number-position:left;
        text-indent:-.25in;
        mso-ansi-font-size:10.0pt;
        font-family:Wingdings;}
@list l5
        {mso-list-id:1807047144;
        mso-list-template-ids:-795822616;}
@list l5:level1
        {mso-level-tab-stop:.5in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l5:level2
        {mso-level-tab-stop:1.0in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l5:level3
        {mso-level-tab-stop:1.5in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l5:level4
        {mso-level-tab-stop:2.0in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l5:level5
        {mso-level-tab-stop:2.5in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l5:level6
        {mso-level-tab-stop:3.0in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l5:level7
        {mso-level-tab-stop:3.5in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l5:level8
        {mso-level-tab-stop:4.0in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l5:level9
        {mso-level-tab-stop:4.5in;
        mso-level-number-position:left;
        text-indent:-.25in;}
@list l6
        {mso-list-id:1910379433;
        mso-list-template-ids:1951670282;}
@list l6:level2
        {mso-level-start-at:0;
        mso-level-number-format:alpha-lower;
        mso-level-tab-stop:none;
        mso-level-number-position:left;
        margin-left:0in;
        text-indent:0in;}
@list l5:level1 lfo2
        {mso-level-start-at:0;
        mso-level-number-format:alpha-lower;
        mso-level-numbering:continue;
        mso-level-tab-stop:none;
        mso-level-number-position:left;
        margin-left:0in;
        text-indent:0in;}
@list l2:level2 lfo7
        {mso-level-start-at:0;
        mso-level-number-format:alpha-lower;
        mso-level-numbering:continue;
        mso-level-text:"%2\.";
        mso-level-tab-stop:none;
        mso-level-number-position:left;
        margin-left:0in;
        text-indent:0in;}
@list l2:level2 lfo8
        {mso-level-start-at:0;
        mso-level-number-format:alpha-upper;
        mso-level-numbering:continue;
        mso-level-text:"%2\.";
        mso-level-tab-stop:none;
        mso-level-number-position:left;
        margin-left:0in;
        text-indent:0in;}
ol
        {margin-bottom:0in;}
ul
        {margin-bottom:0in;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]-->
</head>
<body lang="EN-US" link="#0563C1" vlink="#954F72">
<div class="WordSection1">
<p class="MsoNormal"><span style="color:#1F497D">I&#8217;ve done migrations of this sort several times. I never did a database dump, but instead exported/imported XML, on the premise when doing a database copy, mysql would only tell me about database errors, but
 an export/import would give eprints a chance to tell me about eprints errors.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D"><o:p>&nbsp;</o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D"><o:p>&nbsp;</o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D">On the most recent iteration, moving from 3.2.4 to 3.3.15, I ran into two problems migrating the actual eprints:<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D"><o:p>&nbsp;</o:p></span></p>
<p class="MsoListParagraph" style="text-indent:-.25in;mso-list:l3 level1 lfo1"><![if !supportLists]><span style="color:#1F497D"><span style="mso-list:Ignore">1)<span style="font:7.0pt &quot;Times New Roman&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
</span></span></span><![endif]><span style="color:#1F497D">Exporting was fine, but the import threw a ton of errors. Reversing the .XML file (so newest items were imported first, oldest last) worked. To import in reverse order:<o:p></o:p></span></p>
<p class="MsoListParagraph" style="margin-left:1.0in;text-indent:-.25in;mso-list:l3 level2 lfo1">
<![if !supportLists]><span style="color:#1F497D"><span style="mso-list:Ignore">a.<span style="font:7.0pt &quot;Times New Roman&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
</span></span></span><![endif]>&nbsp;<code><span style="font-size:10.0pt">echo &quot;select eprintid from eprint;&quot; | mysql -u root -p
</span></code><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">ARCHIVEID </span>
<code><span style="font-size:10.0pt">&gt; list.txt</span></code> - get a list of current eprints<span style="color:#1F497D"><o:p></o:p></span></p>
<p class="MsoListParagraph" style="margin-left:1.0in;text-indent:-.25in;mso-list:l3 level2 lfo1">
<![if !supportLists]><span style="color:#1F497D"><span style="mso-list:Ignore">b.<span style="font:7.0pt &quot;Times New Roman&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
</span></span></span><![endif]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">edit
</span><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">list.txt</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"> to
</span><span style="color:#1F497D"><o:p></o:p></span></p>
<p class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;margin-left:1.5in;text-indent:-1.5in;mso-text-indent-alt:-9.0pt;mso-list:l3 level3 lfo1">
<![if !supportLists]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"><span style="mso-list:Ignore"><span style="font:7.0pt &quot;Times New Roman&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
</span>i.<span style="font:7.0pt &quot;Times New Roman&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; </span></span></span><![endif]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">Remove top line, which is &#8220;</span><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">eprints&#8221;</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">
<o:p></o:p></span></p>
<p class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;margin-left:1.5in;text-indent:-1.5in;mso-text-indent-alt:-9.0pt;mso-list:l3 level3 lfo1">
<![if !supportLists]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"><span style="mso-list:Ignore"><span style="font:7.0pt &quot;Times New Roman&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
</span>ii.<span style="font:7.0pt &quot;Times New Roman&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; </span></span></span><![endif]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">Remove any cancelled items. You have to make at least one import attempt to figure out what these
 are.<br>
When you do a full </span><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">export</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">, eprints doesn't emit cancelled or retired items. When you explicitly specify each record to
 export like this, it does. When you import using </span><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">--enable-web-imports</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">, and the new box tries to pull in cancelled or
 retired items, the old box refuses to give up the </span><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">.PDF</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"> files, so you get errors.
<o:p></o:p></span></p>
<p class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;margin-left:1.0in;text-indent:-.25in;mso-list:l3 level2 lfo1">
<![if !supportLists]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"><span style="mso-list:Ignore">c.<span style="font:7.0pt &quot;Times New Roman&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
</span></span></span><![endif]><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">tac &lt; list.txt &gt; revlist.txt</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"> - reverse the list (</span><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">tac</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">
 is </span><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">cat</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"> in reverse)
<o:p></o:p></span></p>
<p class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;margin-left:1.0in;text-indent:-.25in;mso-list:l3 level2 lfo1">
<![if !supportLists]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"><span style="mso-list:Ignore">d.<span style="font:7.0pt &quot;Times New Roman&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
</span></span></span><![endif]><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">tr '\n' ' ' &lt; revlist.txt &gt; revlistspaces.txt</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"> (go from one eprintID per line to a list of space-separated
 eprintIDs) <o:p></o:p></span></p>
<p class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;margin-left:1.0in;text-indent:-.25in;mso-list:l3 level2 lfo1">
<![if !supportLists]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"><span style="mso-list:Ignore">e.<span style="font:7.0pt &quot;Times New Roman&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
</span></span></span><![endif]><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">~/bin/export ARCHIVEID archive XML $(cat revlistspaces.txt) &gt; REV.xml</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">
<o:p></o:p></span></p>
<p class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;margin-left:99.0pt;text-indent:-99.0pt;mso-text-indent-alt:-9.0pt;mso-list:l3 level3 lfo1">
<![if !supportLists]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"><span style="mso-list:Ignore"><span style="font:7.0pt &quot;Times New Roman&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
</span>i.<span style="font:7.0pt &quot;Times New Roman&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; </span></span></span><![endif]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">This depends on pulling the
</span><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">.PDF</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"> files in from the webserver. Use
</span><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">XMLFiles</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"> instead of
</span><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">XML</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"> to get the whole thing Base64-encoded in the
</span><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">.XML</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"> file
<o:p></o:p></span></p>
<p class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;margin-left:99.0pt">
<span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"><o:p>&nbsp;</o:p></span></p>
<p class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;margin-left:.5in;text-indent:-.25in;mso-list:l3 level1 lfo1">
<![if !supportLists]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"><span style="mso-list:Ignore">2)<span style="font:7.0pt &quot;Times New Roman&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
</span></span></span><![endif]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">Thesis info changed somewhere between those two versions<o:p></o:p></span></p>
<p class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;margin-left:1.0in;text-indent:-.25in;mso-list:l3 level2 lfo1">
<![if !supportLists]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"><span style="mso-list:Ignore">a.<span style="font:7.0pt &quot;Times New Roman&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
</span></span></span><![endif]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">Old phd info:
</span><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">&lt;thesis_type&gt;phd&lt;/thesis_type&gt;</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">
<o:p></o:p></span></p>
<p class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;margin-left:1.0in;text-indent:-.25in;mso-list:l3 level2 lfo1">
<![if !supportLists]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"><span style="mso-list:Ignore">b.<span style="font:7.0pt &quot;Times New Roman&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
</span></span></span><![endif]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">Equivalent new phd info:
</span><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">&lt;thesis_type&gt;postdoctoral&lt;/thesis_type&gt;&lt;thesis_name&gt;phd&lt;/thesis_name&gt;</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">
<o:p></o:p></span></p>
<p class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;margin-left:1.0in;text-indent:-.25in;mso-list:l3 level2 lfo1">
<![if !supportLists]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"><span style="mso-list:Ignore">c.<span style="font:7.0pt &quot;Times New Roman&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
</span></span></span><![endif]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">Fixit file :
</span><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">phdfix.sh</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">
<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:99.0pt"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">&nbsp;#!/bin/bash<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.5in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sed 's!&lt;thesis_type&gt;phd&lt;/thesis_type&gt;!&lt;thesis_type&gt;postdoctoral&lt;/thesis_type&gt;&lt;thesis_name&gt;phd&lt;/thesis_name&gt;!' &lt; $1 &gt; $2<o:p></o:p></span></p>
<p class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;margin-left:1.0in;text-indent:-.25in;mso-list:l3 level2 lfo1">
<![if !supportLists]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"><span style="mso-list:Ignore">d.<span style="font:7.0pt &quot;Times New Roman&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
</span></span></span><![endif]><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">./phdfix.sh REV.xml REV_phdfix.xml</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"> (names based on the reversal done above)<o:p></o:p></span></p>
<p class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;margin-left:1.0in;text-indent:-.25in;mso-list:l3 level2 lfo1">
<![if !supportLists]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"><span style="mso-list:Ignore">e.<span style="font:7.0pt &quot;Times New Roman&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
</span></span></span><![endif]><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">~/bin/epadmin erase_data ARCHIVEID
</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">Had some difficulty with
</span><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">erase_eprints</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">, apparently some 'leftovers'. This blows away &amp; rebuilds the entire database.
<o:p></o:p></span></p>
<p class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;margin-left:1.0in;text-indent:-.25in;mso-list:l3 level2 lfo1">
<![if !supportLists]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"><span style="mso-list:Ignore">f.<span style="font:7.0pt &quot;Times New Roman&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
</span></span></span><![endif]><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">~/bin/import_subjects ARCHIVEID</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">
<o:p></o:p></span></p>
<p class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;margin-left:1.0in;text-indent:-.25in;mso-list:l3 level2 lfo1">
<![if !supportLists]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"><span style="mso-list:Ignore">g.<span style="font:7.0pt &quot;Times New Roman&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
</span></span></span><![endif]><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">~/bin/import ARCHIVEID --enable-import-fields --enable-web-imports --update --force --verbose archive XML REV_phdfix.xml</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">
<o:p></o:p></span></p>
<p class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;margin-left:1.5in;text-indent:-1.5in;mso-text-indent-alt:-9.0pt;mso-list:l3 level3 lfo1">
<![if !supportLists]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"><span style="mso-list:Ignore"><span style="font:7.0pt &quot;Times New Roman&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
</span>i.<span style="font:7.0pt &quot;Times New Roman&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; </span></span></span><![endif]><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">--update</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"> overwrites older eprints w/the
 same ID instead of appending them to the end of the collection. <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D"><o:p>&nbsp;</o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D">Once done, verify:<o:p></o:p></span></p>
<ol start="1" type="1">
<li class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;mso-list:l2 level1 lfo6">
<b><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">NEWBox</span></b><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"> :
</span><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">~/bin/export ARCHIVEID archive XML &gt; NEW.xml</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">
<o:p></o:p></span></li><li class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;mso-list:l2 level1 lfo6">
<b><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">OLDBox</span></b><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"> :
</span><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">~/bin/export ARCHIVEID archive XML &gt; OLD.xml</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">
<o:p></o:p></span></li><li class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;mso-list:l2 level1 lfo6">
<span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">massage the files to get rid of known / OK differences
<o:p></o:p></span></li></ol>
<ol start="3" type="1">
<ol start="1" type="a">
<li class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;mso-list:l2 level2 lfo7">
<span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">FILE </span>
<span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sedsOld.sh</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">
<o:p></o:p></span></li></ol>
</ol>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">#!/bin/bash<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"># clean up encoding changes<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">dos2unix $1<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"># name change<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sed -i 's!OLDURL!NEWURL!g' $1<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"># double to single quote<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sed -i &quot;s/\&quot;/'/g&quot; $1<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"># this appears in different spots in old &amp;amp; new formats<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sed -i &quot;s! xmlns='http://eprints.org/ep2/data/2.0'!!&quot; $1<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"># new format uses FQDN<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sed -i 's!&lt;uri&gt;/id/document/!&lt;uri&gt;http://FQDN/id/document/!' $1<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"># these ALL change - import increments them<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sed -i '/&lt;rev_number&gt;.*&lt;\/rev_number&gt;/d' $1<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"># shows up in different spots than new format<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sed -i '/&lt;mime_type&gt;application\/pdf&lt;\/mime_type&gt;/d' $1<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"># quite a few of these empties show in the old format, not the new<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sed -i '/&lt;id&gt;&lt;\/id&gt;/d' $1<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sed -i '/&lt;reported_by&gt;&lt;\/reported_by&gt;/d' $1<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sed -i '/&lt;resolved_by&gt;&lt;\/resolved_by&gt;/d' $1<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sed -i '/&lt;comment&gt;&lt;\/comment&gt;/d' $1<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"># this is an entire multi-line section that lives in the old, but not in the new<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">perl -i -0pe 's/&lt;copies&gt;.*?&lt;\/copies&gt;/DELETEME/sg' $1 # can't easily delete; this replaces with literal DELETEME<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"># Encoding of abstract has changed. Not always visibly obvious how (CRLFs, I think)<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">#perl -i -0pe 's/&lt;abstract&gt;.*?&lt;\/abstract&gt;/DELETEME/sg' $1 # can't easily delete; this replaces with literal DELETEME<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sed -i '/DELETEME/d' $1<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"># thesis type changes between the two versions<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sed -i '/&lt;thesis_type&gt;phd&lt;\/thesis_type&gt;/d' $1<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"># old version encodes dashes; new version uses dashes<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sed -i 's/%2D/-/g' $1<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"># old version encodes this; new version ignores???<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:1.25in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sed -i 's/&amp;#13;//g' $1<o:p></o:p></span></p>
<p class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;margin-left:0in;text-indent:0in;mso-list:l2 level2 lfo7">
<![if !supportLists]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"><span style="mso-list:Ignore">b.<span style="font:7.0pt &quot;Times New Roman&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
</span></span></span><![endif]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">FILE
</span><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sedsNew.sh</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">
<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:.75in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">#!/bin/bash<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:.75in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"><o:p>&nbsp;</o:p></span></p>
<p class="MsoNormal" style="margin-left:.75in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"># clean up encoding changes<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:.75in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">dos2unix $1<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:.75in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"># these ALL change - import increments them<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:.75in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sed -i '/&lt;rev_number&gt;.*&lt;\/rev_number&gt;/d' $1<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:.75in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"># shows up in different spots than new format<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:.75in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sed -i '/&lt;mime_type&gt;application\/pdf&lt;\/mime_type&gt;/d' $1<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:.75in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"># this appears in different spots in old &amp;amp; new formats<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:.75in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sed -i &quot;s! xmlns='http://eprints.org/ep2/data/2.0'!!&quot; $1<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:.75in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"># these are now encoded; old format was not<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:.75in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sed -i &quot;s/&amp;quot;/\'/g&quot; $1<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:.75in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"># these are now encoded; old format was not<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:.75in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sed -i &quot;s/&amp;apos;/\'/g&quot; $1<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:.75in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"># thesis type changes between the two versions<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:.75in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sed -i '/&lt;thesis_type&gt;phd&lt;\/thesis_type&gt;/d' $1<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:.75in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sed -i '/&lt;thesis_type&gt;postdoctoral&lt;\/thesis_type&gt;/d' $1<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:.75in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sed -i '/&lt;thesis_name&gt;phd&lt;\/thesis_name&gt;/d' $1<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:.75in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"># Encoding of abstract has changed. Not always visibly obvious how (CRLFs, I think)<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:.75in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">perl -i -0pe 's/&lt;abstract&gt;.*?&lt;\/abstract&gt;/DELETEME/sg' $1 # can't easily delete; this replaces with DELETEME<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:.75in"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sed -i '/DELETEME/d' $1<o:p></o:p></span></p>
<ol start="4" type="1">
<li class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;mso-list:l2 level1 lfo7">
<span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">diff</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"> the files and see what's left
<o:p></o:p></span></li><li class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;mso-list:l2 level1 lfo7">
<span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">This shows that
</span><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">lastmod</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"> is the date of import on the
</span><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">NEW</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"> file. To set it back to what it was:
<o:p></o:p></span></li></ol>
<p class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;margin-left:.5in;text-indent:-.25in;mso-list:l2 level2 lfo8">
<![if !supportLists]><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"><span style="mso-list:Ignore">&nbsp;.<span style="font:7.0pt &quot;Times New Roman&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
</span></span></span><![endif]><b><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">OLDbox</span></b><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">:
</span><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">echo 'SELECT CONCAT(&quot;update eprint set lastmod_year=&quot;,lastmod_year,&quot;, lastmod_month=&quot;,lastmod_month,&quot;, lastmod_day=&quot;,lastmod_day,&quot;, lastmod_hour=&quot;,lastmod_hour,&quot;, lastmod_minute=&quot;,lastmod_minute,&quot;,
 lastmod_second=&quot;,lastmod_second,&quot; WHERE eprintid=&quot;,eprintid,&quot;;&quot;) FROM eprint;' | mysql -u root -p ARCHIVEID &gt; lastmod.sql</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">
<o:p></o:p></span></p>
<ol start="5" type="1">
<ol start="1" type="A">
<li class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;mso-list:l2 level2 lfo8">
<span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">lastmod.sql</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">, get rid of first line (shows the command that created this file), and prepend the output with
</span><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">use ARCHIVEID;</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">
<o:p></o:p></span></li><li class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;mso-list:l2 level2 lfo8">
<b><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">NEWbox</span></b><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">:
</span><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">mysql -u root -p &lt; lastmod.sql</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">
<o:p></o:p></span></li></ol>
<li class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;mso-list:l2 level1 lfo8">
<span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">REPEAT: Export new / run the seds on new / compare
<o:p></o:p></span></li></ol>
<p class="MsoNormal"><span style="color:#1F497D"><o:p>&nbsp;</o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D">How to migrate the users:<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">*** BEGIN FILE: MigrateUsers.sh</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"> ***<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">#/bin/bash<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"><o:p>&nbsp;</o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">OLDBOX=IP_OR_FQDN<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">OLDMYSQLPWD=PASSWORDGOESHERE<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">NEWMYSQLPWD=PASSWORDGOESHERE<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"><o:p>&nbsp;</o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">ssh root@${OLDBOX} &quot;sudo -u eprints /usr/share/eprints3/bin/export ARCHIVEID user XML&quot; &gt; oldboxusers.xml<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"># HEREDOC to avoid quote escapement torture<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;"># grep to remove the motd lines that get put in there<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">ssh root@${OLDBOX} &lt;&lt;HEREDOC | grep &quot;^update user set password.*&quot; &gt; oldboxpasswords.sql<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">mysql -u root -p${OLDMYSQLPWD} ARCHIVEID --skip-column-names -e 'select concat(&quot;update user set password=\&quot;&quot;, password, &quot;\&quot; where username=\&quot;&quot;, username, &quot;\&quot;;&quot;) from user;'<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">HEREDOC<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">sudo -u eprints /usr/share/eprints3/bin/import ARCHIVEID user XML oldboxusers.xml<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">mysql -u root -p${NEWMYSQLPWD} ARCHIVEID &lt; oldboxpasswords.sql<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">rm oldboxpasswords.sql<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">rm oldboxusers.xml<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt;font-family:&quot;Courier New&quot;">*** END FILE: MigrateUsers.sh</span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"> ***<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D"><o:p>&nbsp;</o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D">Sorry for some of the weird outline-autonumbering &nbsp;/ indentation &#8211; all of this was copied / pasted from my documentation wiki.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D"><o:p>&nbsp;</o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D"><o:p>&nbsp;</o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D">Good luck,<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D">Dan Stieneke<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D">IT Specialist<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D">USDA - ARS - NWISRL<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D">3793 N 3600 E<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D">Kimberly, ID 83341<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D">208/423-6519<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D"><o:p>&nbsp;</o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D"><o:p>&nbsp;</o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D"><o:p>&nbsp;</o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D"><o:p>&nbsp;</o:p></span></p>
<div>
<div style="border:none;border-top:solid #B5C4DF 1.0pt;padding:3.0pt 0in 0in 0in">
<p class="MsoNormal"><b><span style="font-size:10.0pt;font-family:&quot;Tahoma&quot;,&quot;sans-serif&quot;">From:</span></b><span style="font-size:10.0pt;font-family:&quot;Tahoma&quot;,&quot;sans-serif&quot;"> eprints-tech-bounces@ecs.soton.ac.uk [mailto:eprints-tech-bounces@ecs.soton.ac.uk]
<b>On Behalf Of </b>Andrew Beeken<br>
<b>Sent:</b> Friday, January 20, 2017 9:41 AM<br>
<b>To:</b> eprints-tech@ecs.soton.ac.uk<br>
<b>Subject:</b> [EP-tech] Migrating output data - most efficient way<o:p></o:p></span></p>
</div>
</div>
<p class="MsoNormal"><o:p>&nbsp;</o:p></p>
<p class="MsoNormal"><span lang="EN-GB">Hello all!<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB"><o:p>&nbsp;</o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB">So, my quest to get the Lincoln repository onto a more standard EPrints install continues! Thanks for help with Ubuntu versions etc; I&#8217;ve now got that knowledge together and can start to look at the migration. I know
 I&#8217;ve asked this in the past, but my scope has changed slightly. Now, instead of looking at recreating our live repository like for like, I&#8217;m just looking at migrating the output data into a fresh EPrints installation and working from there.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB"><o:p>&nbsp;</o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB">I know I realistically have two options &#8211; importing from an EPrints XML dump off the main site or through a database dump. I&#8217;m assuming that in both cases I&#8217;ll need to bring over essential field definition, phrase and
 workflow files to avoid causing issues, and I&#8217;m assuming that, ideally, the database route would be best to make sure that any &#8220;in review&#8221; or hidden items are also brought across. Main qustions:<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB"><o:p>&nbsp;</o:p></span></p>
<p class="MsoListParagraph" style="text-indent:-.25in"><span lang="EN-GB" style="font-family:Symbol">&middot;</span><span lang="EN-GB" style="font-size:7.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
</span><span lang="EN-GB">Am I right in this assumption?<o:p></o:p></span></p>
<p class="MsoListParagraph" style="text-indent:-.25in"><span lang="EN-GB" style="font-family:Symbol">&middot;</span><span lang="EN-GB" style="font-size:7.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
</span><span lang="EN-GB">Can I JUST bring out a subset of tables for the deposit data or do I have to do a full database export? I&#8217;d ideally prefer to not do the latter as there are customisations to the user table in our live EPrints that I&#8217;m trying to avoid
 replicating in this new environment.<o:p></o:p></span></p>
<p class="MsoListParagraph" style="text-indent:-.25in"><span lang="EN-GB" style="font-family:Symbol">&middot;</span><span lang="EN-GB" style="font-size:7.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
</span><span lang="EN-GB">Are there any gotchas I should be aware of?<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB"><o:p>&nbsp;</o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB">Thanks, as always, in advance!<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-GB">Andrew<o:p></o:p></span></p>
<div>
<p class="MsoNormal"><span lang="EN-GB" style="font-size:10.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"><br>
<b>The University of Lincoln, located in the heart of the city of Lincoln, has established an international reputation based on high student satisfaction, excellent graduate employment and world-class research.</b></span><span lang="EN-GB" style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span lang="EN-GB" style="font-size:7.5pt;font-family:&quot;Arial&quot;,&quot;sans-serif&quot;"><br>
The information in this e-mail and any attachments may be confidential. If you have received this email in error please notify the sender immediately and remove it from your system. Do not disclose the contents to another person or take copies.<br>
<br>
Email is not secure and may contain viruses. The University of Lincoln makes every effort to ensure email is sent without viruses, but cannot guarantee this and recommends recipients take appropriate precautions.<br>
<br>
The University may monitor email traffic data and content in accordance with its policies and English law. Further information can be found at:
<a href="http://www.lincoln.ac.uk/legal">http://www.lincoln.ac.uk/legal</a>.</span><span lang="EN-GB" style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,&quot;serif&quot;"><o:p></o:p></span></p>
</div>
</div>
<br>
<br>
<br>
<br>
This electronic message contains information generated by the USDA solely for the intended recipients. Any unauthorized interception of this message or the use or disclosure of the information it contains may violate the law and subject the violator to civil
 or criminal penalties. If you believe you have received this message in error, please notify the sender and delete the email immediately.
</body>
</html>