[9234] | 1 | package org.greenstone.gsdl3.service;
|
---|
| 2 |
|
---|
| 3 | // Greenstone classes
|
---|
| 4 | import org.greenstone.gdbm.*;
|
---|
| 5 | import org.greenstone.gsdl3.util.*;
|
---|
| 6 |
|
---|
| 7 | // XML classes
|
---|
| 8 | import org.w3c.dom.Element;
|
---|
| 9 | import org.w3c.dom.Document;
|
---|
| 10 | import org.w3c.dom.NodeList;
|
---|
| 11 |
|
---|
| 12 | import java.util.HashMap;
|
---|
| 13 | import java.util.ArrayList;
|
---|
| 14 | import java.io.File;
|
---|
| 15 | import java.io.InputStream;
|
---|
| 16 | import java.io.BufferedReader;
|
---|
| 17 | import java.io.InputStreamReader;
|
---|
| 18 | import java.io.IOException;
|
---|
| 19 | import java.net.HttpURLConnection;
|
---|
| 20 | import java.net.URLConnection;
|
---|
| 21 | import java.net.URL;
|
---|
| 22 | import java.net.Authenticator;
|
---|
| 23 | import java.net.MalformedURLException;
|
---|
| 24 |
|
---|
| 25 | /**
|
---|
| 26 | *
|
---|
| 27 | * @author <a href="mailto:[email protected]">Katherine Don</a>
|
---|
| 28 | * @version $Revision: 9289 $
|
---|
| 29 | * Modified by <a href="mailto:[email protected]">Chi-Yu Huang</a>
|
---|
| 30 | */
|
---|
| 31 |
|
---|
| 32 | public class IViaRetrieve
|
---|
| 33 | extends AbstractDocumentRetrieve {
|
---|
| 34 |
|
---|
| 35 | protected String ivia_server_url = null;
|
---|
| 36 |
|
---|
[9289] | 37 | public IViaRetrieve() {
|
---|
| 38 | does_structure = false;
|
---|
| 39 | }
|
---|
| 40 |
|
---|
[9234] | 41 | //Configure IViaRetrieve Service
|
---|
| 42 | public boolean configure(Element info, Element extra_info)
|
---|
| 43 | {
|
---|
[9289] | 44 | if (!super.configure(info, extra_info)) {
|
---|
| 45 | return false;
|
---|
| 46 | }
|
---|
| 47 |
|
---|
[9234] | 48 | Element server_elem = (Element)GSXML.getChildByTagName(info, "iViaServer");
|
---|
| 49 | if (server_elem == null) {
|
---|
| 50 | System.err.println("IViaRetrieve.configure error: no iViaServer element found");
|
---|
| 51 | return false;
|
---|
| 52 | }
|
---|
| 53 | ivia_server_url = server_elem.getAttribute("url");
|
---|
| 54 | if (ivia_server_url.equals("")) {
|
---|
| 55 | System.err.println("IViaRetrieve.configure error: no url for the iViaServer element");
|
---|
| 56 | return false;
|
---|
| 57 | }
|
---|
| 58 | return true;
|
---|
| 59 |
|
---|
| 60 | }
|
---|
| 61 |
|
---|
| 62 | /** gets a document by sending a request to iVia, then processes it and creates a documentNode around the text */
|
---|
| 63 | protected Element getNodeContent(String doc_id) {
|
---|
| 64 |
|
---|
| 65 | String url_string = ivia_server_url+"/cgi-bin/view_record?theme=gsdl3&record_id="+doc_id;
|
---|
| 66 |
|
---|
| 67 | StringBuffer buffer = new StringBuffer();
|
---|
| 68 | try {
|
---|
| 69 | BufferedReader reader = makeConnection(url_string);
|
---|
| 70 | String line;
|
---|
| 71 | while((line = reader.readLine())!= null) {
|
---|
| 72 | buffer.append(line);
|
---|
| 73 | }
|
---|
| 74 | } catch (Exception e) {
|
---|
| 75 | System.err.println("IViaRetrieve Error:exception happened");
|
---|
| 76 | e.printStackTrace();
|
---|
| 77 | }
|
---|
| 78 |
|
---|
| 79 | String node_content = buffer.toString();
|
---|
| 80 |
|
---|
| 81 | String escaped_content = GSXML.xmlSafe(node_content);
|
---|
| 82 |
|
---|
| 83 | StringBuffer processed_content = new StringBuffer(escaped_content.length());
|
---|
| 84 | processed_content.append("<nodeContent>");
|
---|
| 85 | int pos = 0;
|
---|
| 86 | int lastpos = 0;
|
---|
| 87 | while ((pos = escaped_content.indexOf("<a ", lastpos))!= -1) {
|
---|
| 88 | processed_content.append(escaped_content.substring(lastpos, pos));
|
---|
| 89 | int endpos = escaped_content.indexOf("</a>", pos);
|
---|
| 90 | if (endpos == -1) {
|
---|
| 91 | break;
|
---|
| 92 | }
|
---|
| 93 | String link = escaped_content.substring(pos, endpos+10);
|
---|
| 94 | link = convertLink(link);
|
---|
| 95 | processed_content.append(link);
|
---|
| 96 | lastpos = endpos+10;
|
---|
| 97 | }
|
---|
| 98 | processed_content.append(escaped_content.substring(lastpos)); // get the last bit
|
---|
| 99 | processed_content.append("</nodeContent>");
|
---|
| 100 |
|
---|
| 101 | Element content_element = this.converter.getDOM(processed_content.toString()).getDocumentElement();
|
---|
| 102 |
|
---|
| 103 | return (Element)this.doc.importNode(content_element,true);
|
---|
| 104 | }
|
---|
| 105 |
|
---|
| 106 | /** converts a url from an <a> element into a greenstone suitable one */
|
---|
| 107 | protected String convertLink(String aref) {
|
---|
| 108 | if (aref.indexOf("href="http") != -1) {
|
---|
| 109 | return aref; // an external link
|
---|
| 110 | }
|
---|
| 111 | String type = "other";
|
---|
| 112 | if (aref.indexOf("/cgi-bin/canned_search")!=-1) {
|
---|
| 113 | type="query";
|
---|
| 114 | } else if (aref.indexOf("/cgi-bin/click_through") != -1) {
|
---|
| 115 | type = "external";
|
---|
| 116 | } else if (aref.indexOf("/cgi-bin/view_record") != -1) {
|
---|
| 117 | type="document";
|
---|
| 118 | }
|
---|
| 119 |
|
---|
| 120 | int href_start = aref.indexOf("href="")+11;
|
---|
| 121 | int href_end = aref.indexOf(">", href_start);
|
---|
| 122 | String href = aref.substring(href_start, href_end);
|
---|
| 123 | String link_content = aref.substring(href_end+4, aref.length()-10);
|
---|
| 124 |
|
---|
| 125 | if (type.equals("external")) {
|
---|
| 126 | // the external link is everything after the http at the end.
|
---|
| 127 | String address = href.substring(href.lastIndexOf("http"));
|
---|
| 128 | address = address.replaceAll("%3[aA]", ":");
|
---|
| 129 | address = address.replaceAll("%2[fF]", "/");
|
---|
| 130 |
|
---|
| 131 | return "<a href=\""+address+"\">"+link_content+"</a>";
|
---|
| 132 | }
|
---|
| 133 | if (type.equals("other")) {
|
---|
| 134 | return "other type of link ("+link_content+")";
|
---|
| 135 | }
|
---|
| 136 | StringBuffer result = new StringBuffer();
|
---|
| 137 | result.append("<link type='");
|
---|
| 138 | result.append(type);
|
---|
| 139 | result.append("'");
|
---|
| 140 | if (type.equals("query")) {
|
---|
| 141 | result.append(" service='TextQuery'");
|
---|
| 142 | }
|
---|
| 143 | result.append(">");
|
---|
| 144 | // add in the parameters
|
---|
| 145 | href = href.substring(href.indexOf("?")+1);
|
---|
| 146 | String [] params = href.split("&");
|
---|
| 147 | for (int i=0; i<params.length; i++) {
|
---|
| 148 | String param = params[i];
|
---|
| 149 | int eq_pos = param.indexOf("=");
|
---|
| 150 | if (eq_pos != -1) {
|
---|
| 151 |
|
---|
| 152 | result.append("<param name='"+param.substring(0, eq_pos)+"' value='"+param.substring(eq_pos+1)+"'/>");
|
---|
| 153 | }
|
---|
| 154 | }
|
---|
| 155 | result.append(link_content);
|
---|
| 156 | result.append("</link>");
|
---|
| 157 |
|
---|
| 158 | return result.toString();
|
---|
| 159 | }
|
---|
| 160 |
|
---|
| 161 | // iVia craps out if we ask for a metadata which is not valid. So need
|
---|
| 162 | // to make sure we only ask for acceptable fields.
|
---|
| 163 | protected boolean isAcceptableMetadata(String meta) {
|
---|
| 164 | String valid_metadata = ",title,url,ivia_description,keywords,subjects,";
|
---|
| 165 | if (valid_metadata.indexOf(","+meta+",")!=-1) {
|
---|
| 166 | return true;
|
---|
| 167 | }
|
---|
| 168 | return false;
|
---|
| 169 | }
|
---|
[9289] | 170 |
|
---|
[9234] | 171 | protected BufferedReader makeConnection(String url_string) {
|
---|
| 172 | BufferedReader reader = null;
|
---|
| 173 | try {
|
---|
| 174 | URL url = new URL(url_string);
|
---|
| 175 | HttpURLConnection connection = (HttpURLConnection)url.openConnection();
|
---|
| 176 | InputStream input = connection.getInputStream();
|
---|
| 177 | reader = new BufferedReader(new InputStreamReader(input));
|
---|
| 178 | } catch (java.net.MalformedURLException e) {
|
---|
| 179 | System.err.println("IViaRetrieve: Malformed URL: "+url_string);
|
---|
| 180 | } catch (java.io.IOException e) {
|
---|
| 181 | System.err.println("IViaRetrieve Error: An error occurred during IO to url "+url_string);
|
---|
| 182 | }
|
---|
| 183 | return reader;
|
---|
| 184 | }
|
---|
| 185 |
|
---|
| 186 | protected String translateId(String oid){
|
---|
| 187 | int p = oid.lastIndexOf('.');
|
---|
| 188 | if (p != oid.length()-3) {
|
---|
| 189 | System.out.println("translateoid error: '.' is not the third to last char!!");
|
---|
| 190 | return oid;
|
---|
| 191 | }
|
---|
| 192 | String top = oid.substring(0, p);
|
---|
| 193 | return top;
|
---|
| 194 | }
|
---|
| 195 |
|
---|
| 196 | protected String translateExternalId(String id){
|
---|
| 197 | return id;
|
---|
| 198 | }
|
---|
| 199 |
|
---|
| 200 | protected String getDocType(String node_id){
|
---|
| 201 | return GSXML.DOC_TYPE_SIMPLE;
|
---|
| 202 | }
|
---|
| 203 | protected String getRootId(String node_id){
|
---|
| 204 | return node_id;
|
---|
| 205 | }
|
---|
| 206 |
|
---|
| 207 | protected ArrayList getChildrenIds(String node_id){
|
---|
| 208 | return null;
|
---|
| 209 | }
|
---|
| 210 |
|
---|
| 211 | protected String getParentId(String node_id){
|
---|
| 212 | return null;
|
---|
| 213 | }
|
---|
| 214 |
|
---|
| 215 | protected Element getMetadataList (String doc_id,
|
---|
| 216 | boolean all_metadata,
|
---|
| 217 | ArrayList metadata_names){
|
---|
| 218 |
|
---|
| 219 | Element meta_list = this.doc.createElement(GSXML.METADATA_ELEM+GSXML.LIST_MODIFIER);
|
---|
| 220 |
|
---|
| 221 | // do the query to the iVia server
|
---|
| 222 | StringBuffer field_list= new StringBuffer();
|
---|
| 223 | boolean metadata_found = false;
|
---|
| 224 |
|
---|
| 225 | for (int i=0; i<metadata_names.size();i++){
|
---|
| 226 | if (isAcceptableMetadata((String)metadata_names.get(i))){
|
---|
| 227 | metadata_found = true;
|
---|
| 228 | field_list.append((String)metadata_names.get(i));
|
---|
| 229 | field_list.append(",");
|
---|
| 230 | }
|
---|
| 231 | }
|
---|
| 232 | if (!metadata_found){
|
---|
| 233 | return meta_list;
|
---|
| 234 | }
|
---|
| 235 |
|
---|
| 236 | String url_string = ivia_server_url+"/cgi-bin/view_record_set?theme=gsdl3&record_id_list="+doc_id+"&field_list="+field_list.toString();
|
---|
| 237 | try {
|
---|
| 238 | BufferedReader reader = makeConnection(url_string);
|
---|
| 239 | String line;
|
---|
| 240 | while ((line = reader.readLine()) != null) {
|
---|
| 241 | //metadata entry
|
---|
| 242 | int col_pos = line.indexOf(':');
|
---|
| 243 | if (col_pos == -1) {
|
---|
| 244 | // end of the metadata for this doc
|
---|
| 245 | break;
|
---|
| 246 | }
|
---|
| 247 | String name = line.substring(0,col_pos);
|
---|
| 248 | String value = line.substring(col_pos+2); // includes a space
|
---|
| 249 | GSXML.addMetadata(this.doc, meta_list, name, value);
|
---|
| 250 | }
|
---|
| 251 | } catch (Exception e) {
|
---|
| 252 | System.err.println("IViaRetrieve Error:exception happened");
|
---|
| 253 | e.printStackTrace();
|
---|
| 254 | }
|
---|
| 255 | return meta_list;
|
---|
| 256 | }
|
---|
| 257 |
|
---|
| 258 | protected String getStructureInfo(String doc_id, String info_type){
|
---|
| 259 | return "";
|
---|
| 260 | }
|
---|
| 261 | }
|
---|