[13555] | 1 | /**********************************************************************
|
---|
[8521] | 2 | *
|
---|
[13555] | 3 | * GS2LuceneIndexer.java
|
---|
| 4 | *
|
---|
| 5 | * Copyright 2004 The New Zealand Digital Library Project
|
---|
| 6 | *
|
---|
| 7 | * A component of the Greenstone digital library software
|
---|
| 8 | * from the New Zealand Digital Library Project at the
|
---|
| 9 | * University of Waikato, New Zealand.
|
---|
| 10 | *
|
---|
| 11 | * This program is free software; you can redistribute it and/or modify
|
---|
| 12 | * it under the terms of the GNU General Public License as published by
|
---|
| 13 | * the Free Software Foundation; either version 2 of the License, or
|
---|
| 14 | * (at your option) any later version.
|
---|
| 15 | *
|
---|
| 16 | * This program is distributed in the hope that it will be useful,
|
---|
| 17 | * but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
| 18 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
| 19 | * GNU General Public License for more details.
|
---|
| 20 | *
|
---|
| 21 | * You should have received a copy of the GNU General Public License
|
---|
| 22 | * along with this program; if not, write to the Free Software
|
---|
| 23 | * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
| 24 | *
|
---|
| 25 | *********************************************************************/
|
---|
[8521] | 26 |
|
---|
[13686] | 27 | package org.greenstone.LuceneWrapper;
|
---|
[8521] | 28 |
|
---|
[12257] | 29 |
|
---|
[8521] | 30 | import java.io.*;
|
---|
[10164] | 31 | import java.util.Vector;
|
---|
[8521] | 32 |
|
---|
[16432] | 33 | import org.xml.sax.Attributes;
|
---|
| 34 | import org.xml.sax.helpers.DefaultHandler;
|
---|
| 35 | import org.xml.sax.InputSource;
|
---|
| 36 | import org.xml.sax.SAXException;
|
---|
| 37 | import org.xml.sax.XMLReader;
|
---|
| 38 |
|
---|
| 39 | import javax.xml.parsers.SAXParser;
|
---|
| 40 | import javax.xml.parsers.SAXParserFactory;
|
---|
| 41 |
|
---|
| 42 | import org.apache.lucene.document.Document;
|
---|
| 43 | import org.apache.lucene.document.Field;
|
---|
| 44 | import org.apache.lucene.index.IndexWriter;
|
---|
[16438] | 45 | import org.apache.lucene.index.Term;
|
---|
[17804] | 46 | import org.apache.lucene.analysis.Analyzer;
|
---|
[16432] | 47 |
|
---|
| 48 | import java.util.Stack;
|
---|
| 49 | import java.io.FileInputStream;
|
---|
| 50 | import java.io.File;
|
---|
| 51 | import java.io.StringReader;
|
---|
| 52 | import java.net.URL;
|
---|
| 53 |
|
---|
| 54 |
|
---|
[13555] | 55 | /**
|
---|
| 56 | * class for indexing XML generated by lucenebuildproc.pm
|
---|
| 57 | */
|
---|
| 58 |
|
---|
[8521] | 59 | public class GS2LuceneIndexer {
|
---|
| 60 |
|
---|
[18444] | 61 | protected static boolean debug = false;
|
---|
| 62 |
|
---|
| 63 | protected static void debug(String message)
|
---|
| 64 | {
|
---|
| 65 | if (debug) {
|
---|
| 66 | System.err.println(message);
|
---|
| 67 | }
|
---|
| 68 | }
|
---|
| 69 |
|
---|
| 70 |
|
---|
[10164] | 71 | public static void main (String args[]) throws Exception
|
---|
| 72 | {
|
---|
| 73 | int verbosity = 1;
|
---|
[16262] | 74 | // Default is to edit the existing index
|
---|
| 75 | boolean create_new_index = false;
|
---|
[10164] | 76 |
|
---|
| 77 | Vector filtered_args = new Vector();
|
---|
| 78 |
|
---|
| 79 | int argc = args.length;
|
---|
| 80 | int i = 0;
|
---|
| 81 | while (i<argc) {
|
---|
| 82 | if (args[i].startsWith("-")) {
|
---|
| 83 |
|
---|
[16262] | 84 | // -removeold causes the existing index to be overwritten
|
---|
| 85 | if (args[i].equals("-removeold")) {
|
---|
| 86 | create_new_index = true;
|
---|
[10164] | 87 | }
|
---|
| 88 |
|
---|
| 89 | // -verbosity [num]
|
---|
| 90 | else if (args[i].equals("-verbosity")) {
|
---|
| 91 | i++;
|
---|
| 92 | if (i<argc) {
|
---|
| 93 | verbosity = Integer.parseInt(args[i]);
|
---|
[18444] | 94 | if (verbosity>=5) {
|
---|
| 95 | debug = true;
|
---|
| 96 | }
|
---|
[10164] | 97 | }
|
---|
| 98 | }
|
---|
[18444] | 99 | else if (args[i].equals("-debug")) {
|
---|
| 100 | debug = true;
|
---|
| 101 | }
|
---|
[10164] | 102 | else {
|
---|
| 103 | System.out.println("Unrecognised option: " + args[i]);
|
---|
| 104 | }
|
---|
| 105 | }
|
---|
| 106 | else {
|
---|
| 107 | filtered_args.add((Object)args[i]);
|
---|
| 108 | }
|
---|
| 109 | i++;
|
---|
| 110 | }
|
---|
| 111 |
|
---|
| 112 | if (filtered_args.size() != 3) {
|
---|
[16262] | 113 | System.out.println("Usage: java GS2LuceneIndexer [-removeold|-verbosity [num]] doc-tag-level building_dir index");
|
---|
[8521] | 114 | return;
|
---|
| 115 | }
|
---|
| 116 |
|
---|
[10164] | 117 | String doc_tag_level = (String)filtered_args.get(0);
|
---|
| 118 | String building_dirname = (String)filtered_args.get(1);
|
---|
| 119 | String index_dirname = (String)filtered_args.get(2);
|
---|
[8521] | 120 |
|
---|
| 121 | String import_dirname = building_dirname + File.separator + "text";
|
---|
| 122 |
|
---|
| 123 | File import_dir = new File(import_dirname);
|
---|
| 124 | File building_dir = new File(building_dirname);
|
---|
| 125 |
|
---|
| 126 | if (!import_dir.exists()) {
|
---|
| 127 | System.out.println("Couldn't find import directory: "+import_dirname);
|
---|
| 128 | return;
|
---|
| 129 | }
|
---|
| 130 |
|
---|
| 131 | File idx_dir = new File(building_dir.getPath()+File.separator+index_dirname+File.separator);
|
---|
| 132 | idx_dir.mkdir();
|
---|
| 133 |
|
---|
| 134 | // Set up indexer
|
---|
[16430] | 135 | Indexer indexer = new Indexer(doc_tag_level, idx_dir, create_new_index);
|
---|
[8521] | 136 |
|
---|
| 137 | // Read from stdin the files to process
|
---|
| 138 | try {
|
---|
[9988] | 139 | InputStreamReader isr = new InputStreamReader(System.in, "UTF-8");
|
---|
[8521] | 140 | BufferedReader brin = new BufferedReader(isr);
|
---|
| 141 |
|
---|
| 142 | StringBuffer xml_text = new StringBuffer(1024);
|
---|
| 143 | String line = null;
|
---|
| 144 | while ((line = brin.readLine()) != null) {
|
---|
| 145 | xml_text.append(line);
|
---|
[19861] | 146 | xml_text.append(" ");
|
---|
[18444] | 147 |
|
---|
| 148 | debug("Got line " + line);
|
---|
| 149 |
|
---|
| 150 | if (line.endsWith("</Delete>")) {
|
---|
| 151 |
|
---|
| 152 | indexer.delete(xml_text.toString());
|
---|
| 153 | xml_text = new StringBuffer(1024);
|
---|
| 154 | }
|
---|
| 155 | else if (line.startsWith("</Doc>")) {
|
---|
[16430] | 156 | indexer.index(xml_text.toString());
|
---|
[8521] | 157 | xml_text = new StringBuffer(1024);
|
---|
| 158 | }
|
---|
| 159 | }
|
---|
| 160 |
|
---|
| 161 | brin.close();
|
---|
| 162 | isr.close();
|
---|
| 163 |
|
---|
| 164 | } catch (IOException e) {
|
---|
| 165 | System.err.println("Error: unable to read from stdin");
|
---|
| 166 | e.printStackTrace();
|
---|
| 167 | }
|
---|
| 168 |
|
---|
| 169 | indexer.finish();
|
---|
| 170 | }
|
---|
[16432] | 171 |
|
---|
| 172 |
|
---|
| 173 | static public class Indexer extends DefaultHandler
|
---|
| 174 | {
|
---|
| 175 | IndexWriter writer_ = null;
|
---|
[17804] | 176 | Analyzer analyzer_ = null;
|
---|
[16432] | 177 | SAXParser sax_parser_ = null;
|
---|
| 178 | String doc_tag_level_ = null;
|
---|
| 179 |
|
---|
| 180 | Stack stack_ = null;
|
---|
| 181 | String path_ = "";
|
---|
| 182 |
|
---|
| 183 | Document current_doc_ = null;
|
---|
| 184 | String current_node_ = "";
|
---|
[16438] | 185 | String current_doc_oid_ = "";
|
---|
[16432] | 186 | String indexable_current_node_ = "";
|
---|
| 187 | String current_contents_ = "";
|
---|
| 188 |
|
---|
[18444] | 189 | String mode_ = "";
|
---|
[16432] | 190 | protected String file_id_ = null;
|
---|
| 191 |
|
---|
[17804] | 192 | static private String[] stop_words = GS2Analyzer.STOP_WORDS;
|
---|
| 193 |
|
---|
[18444] | 194 |
|
---|
[16432] | 195 | /** pass in true if want to create a new index, false if want to use the existing one */
|
---|
| 196 | public Indexer (String doc_tag_level, File index_dir, boolean create)
|
---|
| 197 | {
|
---|
| 198 | doc_tag_level_ = doc_tag_level;
|
---|
| 199 |
|
---|
| 200 | try {
|
---|
| 201 | stack_ = new Stack();
|
---|
| 202 | SAXParserFactory sax_factory = SAXParserFactory.newInstance();
|
---|
| 203 | sax_parser_ = sax_factory.newSAXParser();
|
---|
| 204 |
|
---|
| 205 | XMLReader reader = sax_parser_.getXMLReader();
|
---|
| 206 | reader.setFeature("http://xml.org/sax/features/validation", false);
|
---|
| 207 |
|
---|
[17804] | 208 | analyzer_ = new GS2Analyzer(stop_words);
|
---|
| 209 |
|
---|
| 210 | writer_ = new IndexWriter(index_dir.getPath(), analyzer_, create);
|
---|
[16432] | 211 | // by default, will only index 10,000 words per document
|
---|
| 212 | // Can throw out_of_memory errors
|
---|
| 213 | writer_.setMaxFieldLength(Integer.MAX_VALUE);
|
---|
| 214 | if (create) {
|
---|
| 215 | writer_.optimize();
|
---|
| 216 | }
|
---|
| 217 | }
|
---|
[16444] | 218 | catch (Exception e) {
|
---|
| 219 | // We need to know if creating/opening the index fails
|
---|
| 220 | e.printStackTrace();
|
---|
| 221 | }
|
---|
[16432] | 222 | }
|
---|
| 223 |
|
---|
| 224 | /** index one document */
|
---|
| 225 | public void index (String file_id, File file)
|
---|
| 226 | {
|
---|
[18472] | 227 | mode_ = "add";
|
---|
[16432] | 228 | file_id_ = file_id;
|
---|
| 229 | path_ = "";
|
---|
| 230 | String base_path = file.getPath();
|
---|
| 231 | base_path = base_path.substring(0, base_path.lastIndexOf(File.separatorChar));
|
---|
| 232 |
|
---|
| 233 | try {
|
---|
| 234 | sax_parser_.parse(new InputSource(new FileInputStream(file)), this);
|
---|
| 235 | }
|
---|
| 236 | catch (Exception e) {
|
---|
| 237 | println("parse error:");
|
---|
| 238 | e.printStackTrace();
|
---|
| 239 | }
|
---|
| 240 | }
|
---|
| 241 |
|
---|
| 242 | /** index one document stored as string*/
|
---|
| 243 | public void index (String xml_text)
|
---|
| 244 | {
|
---|
[18472] | 245 | mode_ = "add";
|
---|
[16432] | 246 | file_id_ = "<xml doc on stdin>";
|
---|
| 247 | path_ = "";
|
---|
| 248 |
|
---|
| 249 | try {
|
---|
| 250 | sax_parser_.parse(new InputSource(new StringReader(xml_text)), this);
|
---|
| 251 | }
|
---|
| 252 | catch (Exception e) {
|
---|
| 253 | println("parse error:");
|
---|
| 254 | e.printStackTrace();
|
---|
| 255 | }
|
---|
| 256 | }
|
---|
[18444] | 257 |
|
---|
| 258 | /** delete one document, based on doc_id in <Delete>doc_id</Delete> */
|
---|
| 259 | public void delete(String xml_text)
|
---|
| 260 | {
|
---|
| 261 | mode_ = "delete";
|
---|
| 262 | file_id_ = "<delete doc>";
|
---|
| 263 | path_ = "";
|
---|
| 264 |
|
---|
| 265 | try {
|
---|
| 266 | sax_parser_.parse(new InputSource(new StringReader(xml_text)), this);
|
---|
| 267 | }
|
---|
| 268 | catch (Exception e) {
|
---|
| 269 | println("parse error:");
|
---|
| 270 | e.printStackTrace();
|
---|
| 271 | }
|
---|
| 272 | }
|
---|
[16432] | 273 |
|
---|
| 274 | public void finish()
|
---|
| 275 | {
|
---|
| 276 | /** optimise the index */
|
---|
| 277 | try {
|
---|
| 278 | writer_.optimize();
|
---|
| 279 | writer_.close();
|
---|
| 280 | }
|
---|
| 281 | catch (Exception e) {
|
---|
| 282 | }
|
---|
| 283 | }
|
---|
| 284 |
|
---|
| 285 | protected void print(String s)
|
---|
| 286 | {
|
---|
[21957] | 287 | System.err.print(s);
|
---|
[16432] | 288 | }
|
---|
| 289 |
|
---|
| 290 | protected void println(String s)
|
---|
| 291 | {
|
---|
[21957] | 292 | System.err.println(s);
|
---|
[16432] | 293 | }
|
---|
| 294 |
|
---|
| 295 | public void startDocument() throws SAXException
|
---|
| 296 | {
|
---|
[18464] | 297 | println("Starting to process " + file_id_);
|
---|
| 298 | print("[");
|
---|
[16432] | 299 | }
|
---|
| 300 |
|
---|
| 301 | public void endDocument() throws SAXException
|
---|
| 302 | {
|
---|
[18464] | 303 | println("]");
|
---|
| 304 | println("... processing finished.");
|
---|
[16432] | 305 | }
|
---|
| 306 |
|
---|
| 307 | public void startElement(String uri, String localName, String qName, Attributes atts)
|
---|
| 308 | throws SAXException
|
---|
| 309 | {
|
---|
[18464] | 310 | path_ = appendPathLink(path_, qName, atts);
|
---|
| 311 |
|
---|
| 312 | if (qName.equals(doc_tag_level_)) {
|
---|
| 313 | mode_ = atts.getValue("gs2:mode");
|
---|
| 314 |
|
---|
| 315 | pushOnStack(); // start new doc
|
---|
| 316 | current_node_ = qName;
|
---|
[18444] | 317 |
|
---|
[20731] | 318 | //String node_id = atts.getValue("gs2:id");
|
---|
| 319 | //print(" " + qName + ": " + node_id + " (" + mode_ + ")" );
|
---|
| 320 | //current_doc_.add(new Field("nodeID", node_id, Field.Store.YES, Field.Index.UN_TOKENIZED));
|
---|
[18444] | 321 |
|
---|
[18464] | 322 | current_doc_oid_ = atts.getValue("gs2:docOID");
|
---|
[20731] | 323 | print(" " + qName + ": " + current_doc_oid_ + " (" + mode_ + ")" );
|
---|
[18464] | 324 | current_doc_.add(new Field("docOID", current_doc_oid_, Field.Store.YES, Field.Index.UN_TOKENIZED));
|
---|
[16432] | 325 | }
|
---|
[18464] | 326 |
|
---|
| 327 | if (isIndexable(atts)) {
|
---|
| 328 | indexable_current_node_ = qName;
|
---|
| 329 | }
|
---|
| 330 | else {
|
---|
| 331 | indexable_current_node_ = "";
|
---|
| 332 | }
|
---|
[16439] | 333 | }
|
---|
[16432] | 334 |
|
---|
[16439] | 335 | public static boolean isIndexable(Attributes atts)
|
---|
| 336 | {
|
---|
| 337 | boolean is_indexable = false;
|
---|
| 338 |
|
---|
| 339 | String index = atts.getValue("index");
|
---|
| 340 | if (index!=null) {
|
---|
| 341 | if (index.equals("1")) {
|
---|
| 342 | is_indexable = true;
|
---|
| 343 | }
|
---|
| 344 | }
|
---|
| 345 | return is_indexable;
|
---|
[16432] | 346 | }
|
---|
| 347 |
|
---|
| 348 | public void endElement(String uri, String localName, String qName) throws SAXException
|
---|
| 349 | {
|
---|
[18464] | 350 | if (mode_.equals("delete")) {
|
---|
| 351 | try {
|
---|
| 352 | deleteDocument(current_doc_oid_);
|
---|
| 353 | }
|
---|
| 354 | catch (java.io.IOException e) {
|
---|
| 355 | e.printStackTrace();
|
---|
| 356 | }
|
---|
| 357 | }
|
---|
[18472] | 358 | else if (mode_.equals("add") || mode_.equals("update")) {
|
---|
[18444] | 359 | if (qName.equals(indexable_current_node_))
|
---|
| 360 | {
|
---|
| 361 | current_doc_.add(new Field(qName, current_contents_, Field.Store.NO, Field.Index.TOKENIZED, Field.TermVector.YES));
|
---|
| 362 | // The byXX fields are used for sorting search results
|
---|
| 363 | // We don't want to do that for Text or AllFields fields
|
---|
| 364 | // They need to be untokenised for sorting
|
---|
| 365 | if (!qName.equals("TX") && !qName.equals("ZZ"))
|
---|
| 366 | {
|
---|
| 367 | current_doc_.add(new Field("by" + qName, current_contents_, Field.Store.NO, Field.Index.UN_TOKENIZED, Field.TermVector.NO));
|
---|
| 368 | }
|
---|
| 369 |
|
---|
| 370 | current_contents_ = "";
|
---|
| 371 | }
|
---|
| 372 |
|
---|
| 373 | if (qName.equals(doc_tag_level_)) {
|
---|
| 374 | try {
|
---|
[18464] | 375 | // perhaps this is more efficient if addDocument()
|
---|
[18472] | 376 | // used for "add" and updateDocument() for "update"
|
---|
[18444] | 377 | writer_.updateDocument(new Term("docOID", current_doc_oid_), current_doc_, analyzer_);
|
---|
| 378 | }
|
---|
| 379 | catch (java.io.IOException e) {
|
---|
| 380 | e.printStackTrace();
|
---|
| 381 | }
|
---|
| 382 | popOffStack(); // end document
|
---|
[16432] | 383 | }
|
---|
[18444] | 384 |
|
---|
| 385 | path_ = removePathLink(path_);
|
---|
| 386 | }
|
---|
[16432] | 387 | }
|
---|
| 388 |
|
---|
| 389 | public void characters(char ch[], int start, int length) throws SAXException
|
---|
| 390 | {
|
---|
| 391 | String data = new String(ch, start, length).trim();
|
---|
| 392 | if (data.length() > 0 ) {
|
---|
| 393 | current_contents_ += data;
|
---|
| 394 | }
|
---|
| 395 | }
|
---|
| 396 |
|
---|
| 397 | protected String appendPathLink(String path, String qName, Attributes atts)
|
---|
| 398 | {
|
---|
| 399 |
|
---|
| 400 | path = path + "/"+qName;
|
---|
| 401 | if (atts.getLength()>0) {
|
---|
[20731] | 402 | // was gs2:id, changed to gs2:docOID --kjdon
|
---|
| 403 | String id = atts.getValue("gs2:docOID");
|
---|
[16432] | 404 | if (id != null) {
|
---|
[20731] | 405 | path += "[@gs2:docOID='"+id+"']";
|
---|
[16432] | 406 | }
|
---|
| 407 | else {
|
---|
[20731] | 408 | // is this ever used? not in perl currently
|
---|
[16432] | 409 | id = atts.getValue("gs3:id");
|
---|
| 410 | if (id != null) {
|
---|
| 411 | path += "[@gs3:id='"+id+"']";
|
---|
| 412 | }
|
---|
| 413 | }
|
---|
| 414 | }
|
---|
| 415 | return path;
|
---|
| 416 | }
|
---|
| 417 |
|
---|
| 418 | protected String removePathLink(String path)
|
---|
| 419 | {
|
---|
| 420 |
|
---|
| 421 | int i=path.lastIndexOf('/');
|
---|
| 422 | if (i==-1) {
|
---|
| 423 | path="";
|
---|
| 424 | } else {
|
---|
| 425 | path = path.substring(0, i);
|
---|
| 426 | }
|
---|
| 427 | return path;
|
---|
| 428 | }
|
---|
| 429 |
|
---|
| 430 |
|
---|
| 431 | /** these are what we save on the stack */
|
---|
| 432 | private class MyDocument
|
---|
| 433 | {
|
---|
| 434 | public Document doc = null;
|
---|
| 435 | public String contents = null;
|
---|
| 436 | public String tagname = "";
|
---|
| 437 |
|
---|
| 438 | }
|
---|
| 439 |
|
---|
| 440 |
|
---|
| 441 | protected void pushOnStack()
|
---|
| 442 | {
|
---|
| 443 | if (current_doc_ != null) {
|
---|
| 444 | MyDocument save = new MyDocument();
|
---|
| 445 | save.doc = current_doc_;
|
---|
| 446 | save.contents = current_contents_;
|
---|
| 447 | save.tagname = current_node_;
|
---|
| 448 | stack_.push(save);
|
---|
| 449 | }
|
---|
| 450 | current_doc_ = new Document();
|
---|
| 451 | current_contents_ = "";
|
---|
| 452 | current_node_ = "";
|
---|
| 453 | }
|
---|
| 454 |
|
---|
| 455 | protected void popOffStack()
|
---|
| 456 | {
|
---|
| 457 | if (!stack_.empty()) {
|
---|
| 458 | MyDocument saved = (MyDocument)stack_.pop();
|
---|
| 459 | current_doc_ = saved.doc;
|
---|
| 460 | current_contents_ = saved.contents;
|
---|
| 461 | current_node_ = saved.tagname;
|
---|
| 462 | } else {
|
---|
| 463 | current_doc_ = new Document();
|
---|
| 464 | current_contents_ = "";
|
---|
| 465 | current_node_ = "";
|
---|
| 466 | }
|
---|
| 467 | }
|
---|
[18444] | 468 |
|
---|
| 469 |
|
---|
| 470 | protected void deleteDocument(String doc_id)
|
---|
| 471 | throws IOException
|
---|
| 472 | {
|
---|
| 473 | debug("GS2LuceneDelete.deleteDocument(" + doc_id + ")");
|
---|
| 474 | debug("- Initial number of documents in index: " + writer_.docCount());
|
---|
| 475 | writer_.deleteDocuments(new Term("docOID", doc_id));
|
---|
| 476 | debug("- Final number of documents in index: " + writer_.docCount());
|
---|
| 477 | }
|
---|
| 478 |
|
---|
| 479 |
|
---|
[16432] | 480 | }
|
---|
[8521] | 481 | }
|
---|