<%@ page language="java" contentType="text/html; charset=UTF-8" pageEncoding="UTF-8"%>
<%@ page trimDirectiveWhitespaces="true" %>
<%@ page import="org.crosswire.utils.Utils" %>
<%@ page import="org.crosswire.utils.Sessions" %>
<%@ page import="org.crosswire.xml.XMLBlock" %>
<%@ page import="org.crosswire.xml.XMLTag" %>
<%@ page import="org.crosswire.repo.VersionedRepo" %>
<%@ page import="org.crosswire.utils.HTTPUtils" %>
<%@ page import="org.crosswire.sword.keys.VerseKey" %>
<%@ page import="org.crosswire.sword.keys.ListKey" %>
<%@ page import="org.crosswire.community.projects.ntmss.data.Transcription" %>
<%@ page import="org.crosswire.community.projects.ntmss.data.Document" %>
<%@ page import="org.crosswire.community.projects.ntmss.data.Page" %>
<%@ page import="org.crosswire.community.projects.ntmss.data.Transcription.Convert" %>
<%@ page import="org.crosswire.community.projects.ntmss.data.Transcription.Convert.VerseTranscription" %>
<%@ page import="java.util.Map" %>
<%@ page import="java.util.Vector" %>
<%@ page import="org.apache.log4j.Logger" %>
<%
Logger logger = Logger.getLogger("transcript/import");
try {
String sessionHash = Sessions.getSessionHash(request);
String transcript = request.getParameter("text");
int docID = -1; try { docID = Integer.parseInt(request.getParameter("docID")); } catch (Exception e) {}
int pageID = -1; try { pageID = Integer.parseInt(request.getParameter("pageID")); } catch (Exception e) {}
if (transcript != null) transcript = new String(transcript.getBytes("iso8859-1"), "UTF-8");
/*
if (transcript.replaceAll("[a-z,A-Z,0-9<> .:;'\"!,]", "").indexOf("?") == 0) transcript = request.getParameter("text");}
*/
if (transcript != null) {
response.setContentType("text/xml");
Page p = null;
if (docID != -1 && pageID != -1) p = Page.getPage(docID, pageID);
transcript = Transcription.renumberBreaks(transcript, p);
transcript = Transcription.fixTranscription(transcript, p);
out.print(transcript);
return;
}
} catch (Exception e) { e.printStackTrace(); return; }
%>
transcript/clean
Clean TEI, removing unwanted break information and other cruft
Parameters
| text | text of transcription |
| docID | (optional) manuscript id to which this transcript belongs, e.g., 10006 |
| pageID | (optional) manscript page id to which this transcript belongs, e.g., 10 |