<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN"
"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head><meta http-equiv="content-type" content="text/html; charset=utf-8" /><style type="text/css"><!--
#msg dl { border: 1px #006 solid; background: #369; padding: 6px; color: #fff; }
#msg dt { float: left; width: 6em; font-weight: bold; }
#msg dt:after { content:':';}
#msg dl, #msg dt, #msg ul, #msg li, #header, #footer { font-family: verdana,arial,helvetica,sans-serif; font-size: 10pt; }
#msg dl a { font-weight: bold}
#msg dl a:link { color:#fc3; }
#msg dl a:active { color:#ff0; }
#msg dl a:visited { color:#cc6; }
h3 { font-family: verdana,arial,helvetica,sans-serif; font-size: 10pt; font-weight: bold; }
#msg pre, #msg p { overflow: auto; background: #ffc; border: 1px #fc0 solid; padding: 6px; }
#msg ul { overflow: auto; }
#header, #footer { color: #fff; background: #636; border: 1px #300 solid; padding: 6px; }
#patch { width: 100%; }
#patch h4 {font-family: verdana,arial,helvetica,sans-serif;font-size:10pt;padding:8px;background:#369;color:#fff;margin:0;}
#patch .propset h4, #patch .binary h4 {margin:0;}
#patch pre {padding:0;line-height:1.2em;margin:0;}
#patch .diff {width:100%;background:#eee;padding: 0 0 10px 0;overflow:auto;}
#patch .propset .diff, #patch .binary .diff {padding:10px 0;}
#patch span {display:block;padding:0 10px;}
#patch .modfile, #patch .addfile, #patch .delfile, #patch .propset, #patch .binary, #patch .copfile {border:1px solid #ccc;margin:10px 0;}
#patch ins {background:#dfd;text-decoration:none;display:block;padding:0 10px;}
#patch del {background:#fdd;text-decoration:none;display:block;padding:0 10px;}
#patch .lines, .info {color:#888;background:#fff;}
--></style>
<title>[586] blacklight_importer/src/marcoverride/MarcPermissiveStreamReader.java:
Updates to support more permissive reading</title>
</head>
<body>
<div id="msg">
<dl>
<dt>Revision</dt> <dd>586</dd>
<dt>Author</dt> <dd>haschart</dd>
<dt>Date</dt> <dd>2008-06-06 13:41:16 -0400 (Fri, 06 Jun 2008)</dd>
</dl>
<h3>Log Message</h3>
<pre>Updates to support more permissive reading</pre>
<h3>Modified Paths</h3>
<ul>
<li><a href="#blacklight_importersrcmarcoverrideMarcPermissiveStreamReaderjava">blacklight_importer/src/marcoverride/MarcPermissiveStreamReader.java</a></li>
</ul>
</div>
<div id="patch">
<h3>Diff</h3>
<a id="blacklight_importersrcmarcoverrideMarcPermissiveStreamReaderjava"></a>
<div class="modfile"><h4>Modified: blacklight_importer/src/marcoverride/MarcPermissiveStreamReader.java (585 => 586)</h4>
<pre class="diff"><span>
<span class="info">--- blacklight_importer/src/marcoverride/MarcPermissiveStreamReader.java        2008-06-06 17:39:55 UTC (rev 585)
+++ blacklight_importer/src/marcoverride/MarcPermissiveStreamReader.java        2008-06-06 17:41:16 UTC (rev 586)
</span><span class="lines">@@ -356,6 +356,30 @@
</span><span class="cx"> e.printStackTrace();
</span><span class="cx"> }
</span><span class="cx"> }
</span><ins>+ if (permissive && encoding != "UTF-8")
+ {
+ try
+ {
+ utfCheck = new String(recordBuf, "UTF-8");
+ byte byteCheck[] = utfCheck.getBytes("UTF-8");
+ if (recordBuf.length == byteCheck.length)
+ {
+         for (int i = 0; i < recordBuf.length; i++)
+         {
+         if (recordBuf[i] < 0x00 || byteCheck[i] != recordBuf[i])
+         {
+         encoding = "UTF8-Maybe";
+         break;
+         }
+         }
+ }
+ }
+ catch (UnsupportedEncodingException e)
+ {
+ // TODO Auto-generated catch block
+ e.printStackTrace();
+ }
+ }
</ins><span class="cx"> record.setLeader(ldr);
</span><span class="cx">
</span><span class="cx"> if ((directoryLength % 12) != 0)
</span><span class="lines">@@ -809,6 +833,15 @@
</span><span class="cx"> throw new MarcException("unsupported encoding", e);
</span><span class="cx"> }
</span><span class="cx"> }
</span><ins>+ else if (encoding.equals("UTF8-Maybe"))
+ {
+ try {
+ dataElement = new String(bytes, "UTF8");
+ }
+ catch (UnsupportedEncodingException e) {
+ throw new MarcException("unsupported encoding", e);
+ }
+ }
</ins><span class="cx"> else if (encoding.equals("MARC-8") || encoding.equals("MARC8"))
</span><span class="cx"> {
</span><span class="cx"> if (converterAnsel == null) converterAnsel = new AnselToUnicode();
</span></span></pre>
</div>
</div>
</body>
</html>