--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/src/de/mpiwg/dwinter/fulltext/search/xmlsearchadapter/XMLSearchServerAdapter.java	Wed Jan 26 14:41:09 2011 +0100
@@ -0,0 +1,364 @@
+/**
+ * 
+ */
+package de.mpiwg.dwinter.fulltext.search.xmlsearchadapter;
+
+import java.io.File;
+import java.io.FileNotFoundException;
+import java.io.FileOutputStream;
+import java.io.FileWriter;
+import java.io.IOException;
+import java.io.OutputStreamWriter;
+import java.io.UnsupportedEncodingException;
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Set;
+
+import org.apache.log4j.Logger;
+import org.apache.lucene.index.Term;
+import org.apache.lucene.search.Query;
+import org.apache.lucene.search.ScoreDoc;
+import org.apache.lucene.search.TermQuery;
+import org.jdom.Document;
+import org.jdom.Element;
+import org.jdom.JDOMException;
+import org.jdom.input.SAXBuilder;
+import org.jdom.output.Format;
+import org.jdom.output.XMLOutputter;
+import org.jdom.xpath.XPath;
+
+import de.mpiwg.dwinter.fulltext.search.IFulltextSearchDocsLines;
+import de.mpiwg.dwinter.fulltext.search.utils.OCRDoc;
+import de.mpiwg.dwinter.fulltext.search.utils.OCRLine;
+import de.mpiwg.dwinter.fulltext.ticket.TicketWriter;
+import de.mpiwg.dwinter.lucencetools.documents.FileDocument;
+
+/**
+ * @author dwinter
+ * 
+ */
+public class XMLSearchServerAdapter implements IFulltextSearchDocsLines {
+
+	protected static Logger logger = Logger.getRootLogger();
+
+	public static String XMLServerSearchBase = "http://mpdl-test.mpiwg-berlin.mpg.de:30030/mpdl/interface/queryResult.xql?";
+	//public static String XMLDocSearchBase = "http://mpdl-test.mpiwg-berlin.mpg.de:30030/mpdl/interface/doc-query.xql?";
+	public static String XMLDocSearchBase = "http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/page-query-result.xql?";
+	public static String XMLServerBase = "http://mpdl-test.mpiwg-berlin.mpg.de:30030/mpdl/interface/";
+	
+	
+	//http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/page-query-result.xql?document=/echo/la/Bernoulli_1738_AZ870BWE.xml&mode=text&query-type=fulltext&query=quantitas
+	// http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/doc-query.xql?document=/echo/la/Bernoulli_1738_AZ870BWE.xml&queryType=fulltext&query=quantitas
+	/*
+	 * (non-Javadoc)
+	 * 
+	 * @see
+	 * de.mpiwg.dwinter.fulltext.search.IFulltextSearchDocsLines#searchInLinesToDir
+	 * (org.apache.lucene.search.Query, java.lang.String, java.lang.String)
+	 */
+	
+	@Override
+	public void searchInLinesToDir(Query query, String calledLanguage, String ticket)
+			throws IOException {
+		String languageFolderName;
+		String language;
+		//check format of the language string could be lang:xml or just lang
+		String[] langsplitted = calledLanguage.split(":");
+		if(langsplitted.length>1){
+			if(langsplitted[1].equals("XML")){
+				language=langsplitted[0];
+				languageFolderName=calledLanguage;
+			} else {
+				language=calledLanguage;
+				languageFolderName=calledLanguage+":XML";
+			}
+			
+		} else {
+			language=calledLanguage;
+			languageFolderName=calledLanguage+":XML";
+		}
+		
+		
+		
+		TicketWriter tw = new TicketWriter(ticket, query, languageFolderName);
+
+		File languageFile = new File(tw.ticketFile.getAbsolutePath()
+				+ tw.PATHSEPARATOR + languageFolderName);
+		if (!languageFile.exists()) {
+			logger.debug("Create Languagefolder:"
+					+ languageFile.getCanonicalPath());
+			if (!languageFile.mkdirs())
+				throw new IOException();
+		}
+
+		// docbase=archimedes&docbase=echo&queryType=fulltextMorph&language=la&ftMorphQuery=quantitas&pn=1&output=xml&pageSize=50
+		SAXBuilder parser = new SAXBuilder();
+
+		String queryString = XMLServerSearchBase
+				+ "docbase=archimedes&docbase=echo&queryType=fulltextMorph";
+		queryString += "&language=" + language;
+
+		Set<Term> terms = new HashSet<Term>();
+		query.extractTerms(terms);
+		String morphQuery = "";
+		for (Term t : terms) {
+			if (t.field().equals("contents"))
+				morphQuery = t.text();
+		}
+		queryString += "&ftMorphQuery=" + morphQuery;
+		queryString += "&pn=1&output=xml&pageSize=500";
+		Document doc;
+		try {
+			doc = parser.build(queryString);
+		} catch (JDOMException e) {
+			// TODO Auto-generated catch block
+			e.printStackTrace();
+			return;
+		}
+
+		int counter = writeResults(tw, languageFolderName, ticket, doc);
+		writeResultInfo(tw, doc, counter, languageFolderName);
+
+		tw.commitTicket();
+
+		List<Element> docElements;
+		try {
+			XPath docsXP = XPath.newInstance("//document");
+			docElements = docsXP.selectNodes(doc);
+		} catch (JDOMException e1) {
+			// TODO Auto-generated catch block
+			e1.printStackTrace();
+			return;
+		}
+
+		for (Element e : docElements) {
+			Element textIdElement;
+			try {
+				textIdElement = (Element) XPath.selectSingleNode(e, "uri");
+			} catch (JDOMException e1) {
+				// TODO Auto-generated catch block
+				continue;
+			}
+			String textId = textIdElement.getTextTrim();
+
+			File docFile = new File(languageFile.getAbsolutePath()
+					+ TicketWriter.PATHSEPARATOR
+					+ textId.replace(TicketWriter.PATHSEPARATORCHAR, ':'));
+			if (!docFile.exists()) {
+				logger.debug("Create Docfolder:" + docFile.getCanonicalPath());
+				if (!docFile.mkdirs())
+					throw new IOException();
+			}
+
+			// TODO: jetzt fuer jede seite ein file, zur Zeit jeweils nur ein
+			// File pro Document!
+			// for (String page:ocrDoc.linesInPage.keySet()){
+
+			File pageFile = new File(docFile.getAbsolutePath()
+					+ TicketWriter.PATHSEPARATOR
+					+ textId.replace(TicketWriter.PATHSEPARATORCHAR, ':'));
+			FileWriter pageFileWriter = new FileWriter(pageFile);
+			// http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/doc-query.xql?document=/echo/la/Bernoulli_1738_AZ870BWE.xml&queryType=fulltext&query=quantitas
+			http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/page-query-result.xql?document=/echo/la/Bernoulli_1738_AZ870BWE.xml&mode=text&query-type=fulltext&query=quantitas
+			// for (OCRLine line: ocrDoc.linesInPage.get(page)){
+			// pageFileWriter.write("allLines"+"\n");
+			// }
+			queryString = XMLDocSearchBase + "document=" + textId;
+			//queryString += "&queryType=fulltext&query=" + morphQuery;
+			queryString += "&mode=text&query-type=fulltext&query=" + morphQuery;
+
+			try {
+				doc = parser.build(queryString);
+			} catch (JDOMException e2) {
+				// TODO Auto-generated catch block
+				e2.printStackTrace();
+				return;
+			}
+
+			XMLOutputter op = new XMLOutputter(Format.getCompactFormat());
+			op.output(doc, pageFileWriter);
+			pageFileWriter.close();
+		}
+		tw.closeTicket(languageFolderName);
+	}
+
+	private void writeResultInfo(TicketWriter tw, Document doc, int counter,
+			String languageFolderName) throws IOException {
+		//String languageFolderName = language + "_XML";
+
+		File languageFile = new File(tw.ticketFile.getAbsolutePath()
+				+ TicketWriter.PATHSEPARATOR + languageFolderName);
+		File resultFile = new File(languageFile.getAbsolutePath()
+				+ TicketWriter.PATHSEPARATOR + "resultInfo");
+		FileOutputStream fs = new FileOutputStream(resultFile);
+		OutputStreamWriter rw = new OutputStreamWriter(fs, "utf-8");
+		String ret = "<resultInfo>";
+		// int hits = docs.totalHits;
+		ret += "<lang>" + languageFolderName+"</lang>";
+		ret += "<hits>" + counter + "</hits>";
+		ret += "<totalHits>" + counter + "</totalHits>";// TODO: gibt es in
+														// diesem fall einen
+														// unterschied zwischen
+														// hits und totalhits?
+
+		ret += "</resultInfo>";
+		rw.write(ret);
+		rw.close();
+	}
+
+	private int writeResults(TicketWriter tw, String languageFolderName, String ticket,
+			Document doc) throws IOException {
+		OutputStreamWriter rw = null;
+		File languageFile;
+		//String languageFolderName = language + "_XML";
+
+		try {
+			languageFile = new File(tw.ticketFile.getAbsolutePath()
+					+ tw.PATHSEPARATOR + languageFolderName);
+			File resultFile = new File(languageFile.getAbsolutePath()
+					+ tw.PATHSEPARATOR + "result");
+			FileOutputStream fs = new FileOutputStream(resultFile);
+			rw = new OutputStreamWriter(fs, "utf-8");
+		} catch (FileNotFoundException e) {
+			// TODO Auto-generated catch block
+			e.printStackTrace();
+			return -1;
+		} catch (UnsupportedEncodingException e) {
+			// TODO Auto-generated catch block
+			e.printStackTrace();
+			return -1;
+		}
+
+		Set<String> idsAlreadyDone = new HashSet<String>(); // TODO: aus
+															// irgendwelche
+															// gruenden gibt es
+															// ein Dokument
+															// mehrfach in den
+															// Fundstellen
+
+		// FileWriter rw = new FileWriter(resultFile);
+
+		if (!languageFile.exists()) {
+			logger.debug("Create Languagefolder:"
+					+ languageFile.getCanonicalPath());
+			if (!languageFile.mkdirs())
+				throw new IOException();
+		}
+		Integer counter = 0;
+		@SuppressWarnings("unchecked")
+		List<Element> elements;
+		try {
+			XPath xpathDoc = XPath.newInstance("//document");
+			elements = xpathDoc.selectNodes(doc);
+		} catch (JDOMException e1) {
+			// TODO Auto-generated catch block
+			e1.printStackTrace();
+			return -1;
+		}
+
+		for (Element e : elements) {
+			try {
+				XPath xpathUri = XPath.newInstance("uri");
+				Element uri = (Element) xpathUri.selectSingleNode(e);
+
+				String id = uri.getTextTrim();
+				if (!idsAlreadyDone.contains(id)) { // stelle sicher das alle
+													// treffer nur einmal in die
+													// date geschrieben werden.
+					idsAlreadyDone.add(id);
+
+					String textId = id;
+					String md = "";
+					Element mdEl = (Element) XPath
+							.selectSingleNode(e, "author");
+					md += "<dc:creator>" + formatXML(mdEl.getTextTrim())
+							+ "</dc:creator>";
+
+					mdEl = (Element) XPath.selectSingleNode(e, "title");
+					md += "<dc:title>" + formatXML(mdEl.getTextTrim())
+							+ "</dc:title>";
+
+					mdEl = (Element) XPath.selectSingleNode(e, "place");
+					md += "<dc:place>" + formatXML(mdEl.getTextTrim())
+							+ "</dc:place>";
+
+					mdEl = (Element) XPath.selectSingleNode(e, "date");
+					md += "<dc:date>" + formatXML(mdEl.getTextTrim())
+							+ "</dc:date>";
+
+					String ret = "<result xmlns:dc=\"http://dublincore.org/documents/dcmi-namespace/\">";
+					ret += "<cleanedPath>" + textId + "</cleanedPath>";
+					ret += "<textId>" + textId.replace("/", ":") + "</textId>";
+					ret += "<textIdCleaned>" + textId.replace("/", "_")
+							+ "</textIdCleaned>";
+					ret += "<md>" + md + "</md>";
+					ret += "</result>";
+
+					rw.write(ret);
+					counter++;
+				}
+			} catch (JDOMException e1) {
+				// TODO Auto-generated catch block
+				e1.printStackTrace();
+				return -1;
+			}
+		}
+		rw.close();
+		return counter;
+	}
+
+	private String formatXML(String string) {
+		String retStr = string.replace("&", "&amp;");
+		retStr = retStr.replace("<", "&lt;");
+		retStr = retStr.replace(">", "&gt;");
+		return retStr;
+	}
+
+	/*
+	 * (non-Javadoc)
+	 * 
+	 * @see
+	 * de.mpiwg.dwinter.fulltext.search.IFulltextSearchDocsLines#searchInLinesDoc
+	 * (java.lang.String, org.apache.lucene.search.Query, java.lang.String)
+	 */
+	@Override
+	public OCRDoc searchInLinesDoc(String textId, Query query, String language)
+			throws IOException {
+		// TODO Auto-generated method stub
+		return null;
+	}
+
+	/*
+	 * (non-Javadoc)
+	 * 
+	 * @see
+	 * de.mpiwg.dwinter.fulltext.search.IFulltextSearchDocsLines#searchInLines
+	 * (org.apache.lucene.search.Query, java.lang.String)
+	 */
+	@Override
+	public List<OCRDoc> searchInLines(Query query, String language)
+			throws IOException {
+		// TODO Auto-generated method stub
+		return null;
+	}
+
+	public static void main(String[] args) {
+		Term t = new Term("contents", "quantitas");
+		Query q = new TermQuery(t);
+		XMLSearchServerAdapter sa = new XMLSearchServerAdapter();
+		try {
+			sa.searchInLinesToDir(q, "la", "121");
+		} catch (IOException e) {
+			// TODO Auto-generated catch block
+			e.printStackTrace();
+		}
+	}
+
+	public static List<String> getSupportedLanguages() {
+		String langs[] = new String[] { "la:XML", "it:XML" };
+		return Arrays.asList(langs);
+
+	}
+}