1 | /**********************************************************************
|
---|
2 | *
|
---|
3 | * ResultBox.java -- a list of phrases in the Phind java interface
|
---|
4 | *
|
---|
5 | * Copyright 1997-2000 Gordon W. Paynter
|
---|
6 | * Copyright 2000 The New Zealand Digital Library Project
|
---|
7 | *
|
---|
8 | * A component of the Greenstone digital library software
|
---|
9 | * from the New Zealand Digital Library Project at the
|
---|
10 | * University of Waikato, New Zealand.
|
---|
11 | *
|
---|
12 | * This program is free software; you can redistribute it and/or modify
|
---|
13 | * it under the terms of the GNU General Public License as published by
|
---|
14 | * the Free Software Foundation; either version 2 of the License, or
|
---|
15 | * (at your option) any later version.
|
---|
16 | *
|
---|
17 | * This program is distributed in the hope that it will be useful,
|
---|
18 | * but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
19 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
20 | * GNU General Public License for more details.
|
---|
21 | *
|
---|
22 | * You should have received a copy of the GNU General Public License
|
---|
23 | * along with this program; if not, write to the Free Software
|
---|
24 | * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
25 | *
|
---|
26 | *********************************************************************/
|
---|
27 |
|
---|
28 | /*********************************************************************
|
---|
29 |
|
---|
30 | This class is used in the Phind java applet (Phind.java).
|
---|
31 |
|
---|
32 | A ResultBox holds the results of a query to phindcgi. They deal mostly
|
---|
33 | with the information content of the query, and have methods for parsing the
|
---|
34 | input into phrase and document items. They have little do with display:
|
---|
35 | ResultBoxes are shown to the user through "ResultDisplay" panels, and are
|
---|
36 | drawn using "ResultCanvas" objects.
|
---|
37 |
|
---|
38 | **********************************************************************/
|
---|
39 |
|
---|
40 | package org.nzdl.gsdl.Phind;
|
---|
41 |
|
---|
42 | import java.awt.Panel;
|
---|
43 | import java.awt.BorderLayout;
|
---|
44 | import java.awt.Scrollbar;
|
---|
45 |
|
---|
46 | import java.awt.Label;
|
---|
47 | import java.awt.Event;
|
---|
48 |
|
---|
49 | import java.net.*;
|
---|
50 | import java.applet.*;
|
---|
51 |
|
---|
52 | import java.util.Vector;
|
---|
53 |
|
---|
54 |
|
---|
55 | public class ResultBox extends Panel {
|
---|
56 |
|
---|
57 | // Objects at a "higher" level than this one
|
---|
58 | Phind phind;
|
---|
59 | ResultDisplay display;
|
---|
60 |
|
---|
61 | // Surroundig objects
|
---|
62 | ResultBox prev, next;
|
---|
63 |
|
---|
64 | // The components contained by this one.
|
---|
65 | ResultCanvas c;
|
---|
66 | ResultTitle t;
|
---|
67 | Scrollbar s;
|
---|
68 | Panel label;
|
---|
69 |
|
---|
70 | // The key identifying the phrase displayed, with its text and the
|
---|
71 | // collection from which it is drawn
|
---|
72 | String searchKey, searchPhrase, searchCollection;
|
---|
73 |
|
---|
74 | // The total frequency, expansion frequency, and document frequency
|
---|
75 | // of the phrase
|
---|
76 | int numberOfOccurances;
|
---|
77 | int numberOfExpansions;
|
---|
78 | int numberOfDocuments;
|
---|
79 | int numberOfThesaurusLinks;
|
---|
80 |
|
---|
81 | // The number of phrases and documents retrieved, and the number of
|
---|
82 | // times the user has requested more phrases or documents.
|
---|
83 | int expansionsRetrieved;
|
---|
84 | int documentsRetrieved;
|
---|
85 | int thesaurusLinksRetrieved;
|
---|
86 | int nextPhraseBlock;
|
---|
87 | int nextDocumentBlock;
|
---|
88 | int nextThesaurusLinkBlock;
|
---|
89 |
|
---|
90 | int mode;
|
---|
91 | final int initMode = 0;
|
---|
92 | public final int emptyMode = 1;
|
---|
93 | final int loadingMode = 2;
|
---|
94 | final int finishedMode = 3;
|
---|
95 |
|
---|
96 | String buffer;
|
---|
97 | boolean finished;
|
---|
98 |
|
---|
99 |
|
---|
100 | // Create a ResultBox
|
---|
101 | // given details of the search that generated it.
|
---|
102 | ResultBox(Phind p, String collect, String key, String phrase, ResultBox rb) {
|
---|
103 |
|
---|
104 | super();
|
---|
105 | mode = initMode;
|
---|
106 |
|
---|
107 | phind = p;
|
---|
108 | display = null;
|
---|
109 | next = null;
|
---|
110 | prev = rb;
|
---|
111 | if (prev != null) prev.next = this;
|
---|
112 |
|
---|
113 | searchKey = key;
|
---|
114 | searchPhrase = phrase;
|
---|
115 | searchCollection = collect;
|
---|
116 |
|
---|
117 | numberOfOccurances = -1;
|
---|
118 | numberOfExpansions = -1;
|
---|
119 | numberOfDocuments = -1;
|
---|
120 | numberOfThesaurusLinks = -1;
|
---|
121 |
|
---|
122 | expansionsRetrieved = 0;
|
---|
123 | documentsRetrieved = 0;
|
---|
124 | thesaurusLinksRetrieved = 0;
|
---|
125 |
|
---|
126 | nextPhraseBlock = 1;
|
---|
127 | nextDocumentBlock = 1;
|
---|
128 | nextThesaurusLinkBlock = 1;
|
---|
129 |
|
---|
130 |
|
---|
131 | setLayout(new BorderLayout());
|
---|
132 |
|
---|
133 | s = new Scrollbar(Scrollbar.VERTICAL);
|
---|
134 | disableScrollbar();
|
---|
135 | add("East", s);
|
---|
136 |
|
---|
137 | c = new ResultCanvas(this);
|
---|
138 | add("Center", c);
|
---|
139 |
|
---|
140 | t = new ResultTitle(this);
|
---|
141 | add("North", t);
|
---|
142 |
|
---|
143 | buffer = "";
|
---|
144 | finished = false;
|
---|
145 | mode = emptyMode;
|
---|
146 | }
|
---|
147 |
|
---|
148 | static String describeContents(String phrase, String c) {
|
---|
149 | return( "\"" + phrase + "\" in " + c + ".");
|
---|
150 | }
|
---|
151 |
|
---|
152 | String describeContents() {
|
---|
153 | return( describeContents(searchPhrase, searchCollection) );
|
---|
154 | }
|
---|
155 |
|
---|
156 |
|
---|
157 | // Reset the contents of the box
|
---|
158 | void resetBox( ) {
|
---|
159 | buffer = "";
|
---|
160 | finished = false;
|
---|
161 | c.resetCanvas();
|
---|
162 | disableScrollbar();
|
---|
163 | mode = emptyMode;
|
---|
164 |
|
---|
165 | numberOfExpansions = -1;
|
---|
166 | numberOfDocuments = -1;
|
---|
167 | numberOfThesaurusLinks = -1;
|
---|
168 |
|
---|
169 | expansionsRetrieved = 0;
|
---|
170 | documentsRetrieved = 0;
|
---|
171 | thesaurusLinksRetrieved = 0;
|
---|
172 | }
|
---|
173 |
|
---|
174 | void setStatus( String status ) {
|
---|
175 | phind.setStatus(status);
|
---|
176 | }
|
---|
177 |
|
---|
178 | void disableScrollbar() {
|
---|
179 | if (s.isEnabled()) {
|
---|
180 | s.setValues(0, 1, 0, 1);
|
---|
181 | s.setLineIncrement(1);
|
---|
182 | s.setPageIncrement(1);
|
---|
183 | s.disable();
|
---|
184 | }
|
---|
185 | }
|
---|
186 |
|
---|
187 | // Are there displays previous to and after this?
|
---|
188 | public boolean prevBoxExists () {
|
---|
189 | return (prev != null);
|
---|
190 | }
|
---|
191 | public boolean nextBoxExists () {
|
---|
192 | return (next != null);
|
---|
193 | }
|
---|
194 |
|
---|
195 |
|
---|
196 | // Look up a phrase
|
---|
197 | // Phrase lookups are passed on to the Phind applet itself.
|
---|
198 | void lookupPhrase(String key, String phrase, int queryMode) {
|
---|
199 | buffer = "";
|
---|
200 | finished = false;
|
---|
201 | phind.searchForPhrase(this, key, phrase, queryMode);
|
---|
202 | t.repaint();
|
---|
203 | }
|
---|
204 |
|
---|
205 | public boolean handleEvent(Event event) {
|
---|
206 | // System.out.println("event: " + event.toString());
|
---|
207 | if ( (event.target == s) &&
|
---|
208 | ( (event.id == Event.SCROLL_ABSOLUTE) ||
|
---|
209 | (event.id == Event.SCROLL_LINE_DOWN) ||
|
---|
210 | (event.id == Event.SCROLL_LINE_UP) ||
|
---|
211 | (event.id == Event.SCROLL_PAGE_DOWN) ||
|
---|
212 | (event.id == Event.SCROLL_PAGE_UP) ) ) {
|
---|
213 | c.repaint();
|
---|
214 | return true;
|
---|
215 | } else {
|
---|
216 | return super.handleEvent(event);
|
---|
217 | }
|
---|
218 | }
|
---|
219 |
|
---|
220 |
|
---|
221 | // a new section of the byte stream is read
|
---|
222 | void parseBytes(byte[] bytes) {
|
---|
223 | mode = loadingMode;
|
---|
224 |
|
---|
225 | // update the buffer that holds the bytes read
|
---|
226 | String input;
|
---|
227 | try {
|
---|
228 | input = new String(bytes, new String("UTF8"));
|
---|
229 | } catch (Exception e) {
|
---|
230 | System.err.println(e);
|
---|
231 | input = "";
|
---|
232 | }
|
---|
233 | buffer = buffer.concat(input);
|
---|
234 |
|
---|
235 | // Parse each line until there are no more lines to parse
|
---|
236 | while(parseLine());
|
---|
237 |
|
---|
238 | if (finished) {
|
---|
239 | c.updateMarkers();
|
---|
240 | buffer = "";
|
---|
241 | } else {
|
---|
242 | // We haven't finished, give some feedback about progress
|
---|
243 | setStatus("Connected to host, " + c.numberOfItems + " results read");
|
---|
244 | }
|
---|
245 | }
|
---|
246 |
|
---|
247 | // Parse a line of XML
|
---|
248 | //
|
---|
249 | // This isn't necessarily real XML. We assume every tag begins and
|
---|
250 | // ends on one line. We read one line out of the buffer at a time,
|
---|
251 | // then "add" them to the box with the addLine method.
|
---|
252 | //
|
---|
253 | // Return true if there is a another line here to parse, otherwise false.
|
---|
254 |
|
---|
255 | boolean parseLine() {
|
---|
256 |
|
---|
257 | // System.out.print("parseLine " + "(length " + buffer.length() + ")");
|
---|
258 | String item;
|
---|
259 | int eol = buffer.indexOf((int) '\n');
|
---|
260 |
|
---|
261 | // If there are no carriage returns, the line is incomplete
|
---|
262 | if (eol == -1) {
|
---|
263 | return false;
|
---|
264 | }
|
---|
265 |
|
---|
266 | // The </phinddata> tag concludes the dataset
|
---|
267 | else if (buffer.startsWith("</phinddata>")) {
|
---|
268 | mode = finishedMode;
|
---|
269 | finished = true;
|
---|
270 | return false;
|
---|
271 | }
|
---|
272 |
|
---|
273 | // The <expansion> tag
|
---|
274 | else if (buffer.startsWith("<expansion ")) {
|
---|
275 | item = buffer.substring(0, eol);
|
---|
276 | buffer = buffer.substring(eol + 1);
|
---|
277 | addExpansionTag(item);
|
---|
278 | return true;
|
---|
279 | }
|
---|
280 |
|
---|
281 | // The <document> tag
|
---|
282 | else if (buffer.startsWith("<document ")) {
|
---|
283 | item = buffer.substring(0, eol);
|
---|
284 | buffer = buffer.substring(eol + 1);
|
---|
285 | addDocumentTag(item);
|
---|
286 | return true;
|
---|
287 | }
|
---|
288 |
|
---|
289 | // The <thesaurus> tag
|
---|
290 | else if (buffer.startsWith("<thesaurus ")) {
|
---|
291 | item = buffer.substring(0, eol);
|
---|
292 | buffer = buffer.substring(eol + 1);
|
---|
293 | addThesaurusTag(item);
|
---|
294 | return true;
|
---|
295 | }
|
---|
296 |
|
---|
297 | // The <phinddata> tag introduces the dataset
|
---|
298 | else if (buffer.startsWith("<phinddata ")) {
|
---|
299 | item = buffer.substring(0, eol);
|
---|
300 | buffer = buffer.substring(eol + 1);
|
---|
301 | addPhinddataTag(item);
|
---|
302 | return true;
|
---|
303 | }
|
---|
304 |
|
---|
305 | // The <phinderror> tag contains an error message
|
---|
306 | else if (buffer.startsWith("<phinderror")) {
|
---|
307 | item = buffer.substring(0, eol);
|
---|
308 | System.out.println("phind reported an error: " + item);
|
---|
309 | buffer = buffer.substring(eol + 1);
|
---|
310 | return true;
|
---|
311 | }
|
---|
312 |
|
---|
313 | // Ignore the piece we've read
|
---|
314 | item = buffer.substring(0, eol);
|
---|
315 | // System.out.println("discarding: " + item);
|
---|
316 | buffer = buffer.substring(eol + 1);
|
---|
317 | return true;
|
---|
318 | }
|
---|
319 |
|
---|
320 |
|
---|
321 |
|
---|
322 | // Add a phinddata tag
|
---|
323 | //
|
---|
324 | // Given a string containing an XML phinddata tag of the form:
|
---|
325 | // <phinddata id="35" text="FOREST" df="797" ef="134">
|
---|
326 | // Read the expansion information from the tag
|
---|
327 | //
|
---|
328 | // Return true if successful, otherwise false.
|
---|
329 |
|
---|
330 | boolean addPhinddataTag( String line ) {
|
---|
331 |
|
---|
332 | // System.out.println( "addExpansionListTag: " + line);
|
---|
333 |
|
---|
334 | String idStr = "", text = "", tfStr = "", efStr = "", dfStr = "", lfStr = "";
|
---|
335 | int tf = 0, ef = 0, df = 0, lf = 0;
|
---|
336 |
|
---|
337 | // Break the tag down into its component parts
|
---|
338 | int nextSplit;
|
---|
339 | while (line.length() > 0) {
|
---|
340 | line = line.trim();
|
---|
341 |
|
---|
342 | // Read the phrase identifier
|
---|
343 | if (line.startsWith("id")) {
|
---|
344 | line = line.substring(4);
|
---|
345 | nextSplit = line.indexOf((int) '"');
|
---|
346 | if (nextSplit >= 1) {
|
---|
347 | idStr = line.substring(0, nextSplit);
|
---|
348 | line = line.substring(nextSplit + 1);
|
---|
349 | } else {
|
---|
350 | System.err.println("addExpansionListTag: error parsing: " + line);
|
---|
351 | }
|
---|
352 | }
|
---|
353 |
|
---|
354 | // Read the total frequency
|
---|
355 | else if (line.startsWith("tf")) {
|
---|
356 | line = line.substring(4);
|
---|
357 | nextSplit = line.indexOf((int) '"');
|
---|
358 | if (nextSplit >= 1) {
|
---|
359 | tfStr = line.substring(0, nextSplit);
|
---|
360 | tf = Integer.valueOf(tfStr).intValue();
|
---|
361 | line = line.substring(nextSplit + 1);
|
---|
362 | } else {
|
---|
363 | System.err.println("addExpansionListTag: error parsing: " + line);
|
---|
364 | }
|
---|
365 | }
|
---|
366 |
|
---|
367 | // Read the text of the phrase
|
---|
368 | else if (line.startsWith("text")) {
|
---|
369 | line = line.substring(6);
|
---|
370 | nextSplit = line.indexOf((int) '"');
|
---|
371 | if (nextSplit >= 1) {
|
---|
372 | text = line.substring(0, nextSplit);
|
---|
373 | line = line.substring(nextSplit + 1);
|
---|
374 | } else {
|
---|
375 | System.err.println("addExpansionListTag: error parsing: " + line);
|
---|
376 | }
|
---|
377 | }
|
---|
378 |
|
---|
379 | // Read the expansion frequency
|
---|
380 | else if (line.startsWith("ef")) {
|
---|
381 | line = line.substring(4);
|
---|
382 | nextSplit = line.indexOf((int) '"');
|
---|
383 | if (nextSplit >= 1) {
|
---|
384 | efStr = line.substring(0, nextSplit);
|
---|
385 | ef = Integer.valueOf(efStr).intValue();
|
---|
386 | line = line.substring(nextSplit + 1);
|
---|
387 | } else {
|
---|
388 | System.err.println("addExpansionListTag: error parsing: " + line);
|
---|
389 | }
|
---|
390 | }
|
---|
391 |
|
---|
392 | // Read the document frequency
|
---|
393 | else if (line.startsWith("df")) {
|
---|
394 | line = line.substring(4);
|
---|
395 | nextSplit = line.indexOf((int) '"');
|
---|
396 | if (nextSplit >= 1) {
|
---|
397 | dfStr = line.substring(0, nextSplit);
|
---|
398 | df = Integer.valueOf(dfStr).intValue();
|
---|
399 | line = line.substring(nextSplit + 1);
|
---|
400 | } else {
|
---|
401 | System.err.println("addExpansionListTag: error parsing: " + line);
|
---|
402 | }
|
---|
403 | }
|
---|
404 |
|
---|
405 | // Read the thesaurus link frequency
|
---|
406 | else if (line.startsWith("lf")) {
|
---|
407 | line = line.substring(4);
|
---|
408 | nextSplit = line.indexOf((int) '"');
|
---|
409 | if (nextSplit >= 1) {
|
---|
410 | lfStr = line.substring(0, nextSplit);
|
---|
411 | lf = Integer.valueOf(lfStr).intValue();
|
---|
412 | line = line.substring(nextSplit + 1);
|
---|
413 | } else {
|
---|
414 | System.err.println("addExpansionListTag: error parsing: " + line);
|
---|
415 | }
|
---|
416 | }
|
---|
417 |
|
---|
418 | // Read and ignore some other tag
|
---|
419 | else {
|
---|
420 | nextSplit = line.indexOf((int) ' ');
|
---|
421 | if (nextSplit >= 1) {
|
---|
422 | line = line.substring(nextSplit + 1);
|
---|
423 | } else {
|
---|
424 | line = "";
|
---|
425 | }
|
---|
426 | }
|
---|
427 | }
|
---|
428 |
|
---|
429 | // Add the data to the ResultBox
|
---|
430 | searchKey = idStr;
|
---|
431 | searchPhrase = text;
|
---|
432 | numberOfOccurances = tf;
|
---|
433 | numberOfExpansions = ef;
|
---|
434 | numberOfDocuments = df;
|
---|
435 | numberOfThesaurusLinks = lf;
|
---|
436 | return true;
|
---|
437 | }
|
---|
438 |
|
---|
439 |
|
---|
440 | // Add an expansion tag
|
---|
441 | //
|
---|
442 | // Given a string containing an XML expansin tag of the form:
|
---|
443 | // <expansion num="3" id="8421" prefix="PEOPLE and" suffix="" tf="3" df="3"/>
|
---|
444 | // <expansion num="4" id="8696" prefix="" suffix="products" tf="3" df="3"/>
|
---|
445 | // Create a new ResultItemPhrase for display
|
---|
446 | //
|
---|
447 | // Return true if successful, otherwise false.
|
---|
448 |
|
---|
449 | boolean addExpansionTag( String line ) {
|
---|
450 |
|
---|
451 | // System.out.println( "addExpansionTag: " + line + " (" + expansionsRetrieved + ")");
|
---|
452 |
|
---|
453 | String numStr = "", idStr = "", tfStr = "", dfStr = "",
|
---|
454 | prefix = "", body = "", suffix = "";
|
---|
455 |
|
---|
456 | body = searchPhrase;
|
---|
457 |
|
---|
458 | // Break the tag down into its component parts
|
---|
459 | line = line.substring(11);
|
---|
460 | int nextSplit;
|
---|
461 | while (line.length() > 0) {
|
---|
462 | line = line.trim();
|
---|
463 |
|
---|
464 | // Read the expansion number
|
---|
465 | if (line.startsWith("num")) {
|
---|
466 | line = line.substring(5);
|
---|
467 | nextSplit = line.indexOf((int) '"');
|
---|
468 | if (nextSplit >= 1) {
|
---|
469 | numStr = line.substring(0, nextSplit);
|
---|
470 | line = line.substring(nextSplit + 1);
|
---|
471 | } else {
|
---|
472 | System.err.println("ResultBox addExpansionTag: error parsing: " + line);
|
---|
473 | }
|
---|
474 | }
|
---|
475 |
|
---|
476 | // Read the phrase ID
|
---|
477 | else if (line.startsWith("id")) {
|
---|
478 | line = line.substring(4);
|
---|
479 | nextSplit = line.indexOf((int) '"');
|
---|
480 | if (nextSplit >= 1) {
|
---|
481 | idStr = line.substring(0, nextSplit);
|
---|
482 | line = line.substring(nextSplit + 1);
|
---|
483 | } else {
|
---|
484 | System.err.println("ResultBox addExpansionTag: error parsing: " + line);
|
---|
485 | }
|
---|
486 | }
|
---|
487 |
|
---|
488 | // Read the prefix of the phrase
|
---|
489 | else if (line.startsWith("prefix")) {
|
---|
490 | line = line.substring(8);
|
---|
491 | nextSplit = line.indexOf((int) '"');
|
---|
492 | if (nextSplit >= 0) {
|
---|
493 | prefix = line.substring(0, nextSplit);
|
---|
494 | line = line.substring(nextSplit + 1);
|
---|
495 | } else {
|
---|
496 | System.err.println("ResultBox addExpansionTag: error parsing: " + line);
|
---|
497 | }
|
---|
498 | }
|
---|
499 |
|
---|
500 | // Read the suffix of the phrase
|
---|
501 | else if (line.startsWith("suffix")) {
|
---|
502 | line = line.substring(8);
|
---|
503 | nextSplit = line.indexOf((int) '"');
|
---|
504 | if (nextSplit >= 0) {
|
---|
505 | suffix = line.substring(0, nextSplit);
|
---|
506 | line = line.substring(nextSplit + 1);
|
---|
507 | } else {
|
---|
508 | System.err.println("ResultBox addExpansionTag: error parsing: " + line);
|
---|
509 | }
|
---|
510 | }
|
---|
511 |
|
---|
512 | // Read the frequency
|
---|
513 | else if (line.startsWith("tf")) {
|
---|
514 | line = line.substring(4);
|
---|
515 | nextSplit = line.indexOf((int) '"');
|
---|
516 | if (nextSplit >= 1) {
|
---|
517 | tfStr = line.substring(0, nextSplit);
|
---|
518 | line = line.substring(nextSplit + 1);
|
---|
519 | } else {
|
---|
520 | System.err.println("ResultBox addExpansionTag: error parsing: " + line);
|
---|
521 | }
|
---|
522 | }
|
---|
523 |
|
---|
524 | // Read the document frequency
|
---|
525 | else if (line.startsWith("df")) {
|
---|
526 | line = line.substring(4);
|
---|
527 | nextSplit = line.indexOf((int) '"');
|
---|
528 | if (nextSplit >= 1) {
|
---|
529 | dfStr = line.substring(0, nextSplit);
|
---|
530 | line = line.substring(nextSplit + 1);
|
---|
531 | } else {
|
---|
532 | System.err.println("ResultBox addExpansionTag: error parsing: " + line);
|
---|
533 | }
|
---|
534 | }
|
---|
535 |
|
---|
536 | // Read some other tag
|
---|
537 | else {
|
---|
538 | nextSplit = line.indexOf((int) ' ');
|
---|
539 | if (nextSplit >= 1) {
|
---|
540 | line = line.substring(nextSplit + 1);
|
---|
541 | } else {
|
---|
542 | line = "";
|
---|
543 | }
|
---|
544 | }
|
---|
545 | }
|
---|
546 |
|
---|
547 | // Create a new ResultItem and add it to the display
|
---|
548 | ResultItemPhrase ri = new ResultItemPhrase(idStr, tfStr, dfStr, prefix, body, suffix);
|
---|
549 |
|
---|
550 | if (c.addResultItem(ri)) {
|
---|
551 | expansionsRetrieved++;
|
---|
552 | return true;
|
---|
553 | }
|
---|
554 |
|
---|
555 | return false;
|
---|
556 | }
|
---|
557 |
|
---|
558 |
|
---|
559 | // Add an document tag
|
---|
560 | //
|
---|
561 | // Given a string containing an XML document tag of the form:
|
---|
562 | // <document num="2" hash="HASH424e64b811fdad933be69c" freq="1" title="CONTENTS"/>
|
---|
563 | // <document num="3" hash="HASH01f08efd8752ad54ca0a99cf" freq="1" title="Tree mixtures"/>
|
---|
564 | //
|
---|
565 | // Create a new ResultItemDocument for display
|
---|
566 | //
|
---|
567 | // Return true if successful, otherwise false.
|
---|
568 |
|
---|
569 | boolean addDocumentTag( String line ) {
|
---|
570 |
|
---|
571 | // System.out.println( "addDocumentTag: " + line + " (" + documentsRetrieved + ")");
|
---|
572 |
|
---|
573 | String num = "", hash = "", freq = "", title = "";
|
---|
574 | line = line.substring(9);
|
---|
575 |
|
---|
576 | // Break the tag down into its component parts
|
---|
577 | int nextSplit;
|
---|
578 | while (line.length() > 0) {
|
---|
579 | line = line.trim();
|
---|
580 |
|
---|
581 | // Read the expansion number
|
---|
582 | if (line.startsWith("num")) {
|
---|
583 | line = line.substring(5);
|
---|
584 | nextSplit = line.indexOf((int) '"');
|
---|
585 | if (nextSplit >= 1) {
|
---|
586 | num = line.substring(0, nextSplit);
|
---|
587 | line = line.substring(nextSplit + 1);
|
---|
588 | } else {
|
---|
589 | System.err.println("ResultBox addDocumentTag: error parsing: " + line);
|
---|
590 | }
|
---|
591 | }
|
---|
592 |
|
---|
593 | // Read the document OID hash
|
---|
594 | else if (line.startsWith("hash")) {
|
---|
595 | line = line.substring(6);
|
---|
596 | nextSplit = line.indexOf((int) '"');
|
---|
597 | if (nextSplit >= 1) {
|
---|
598 | hash = line.substring(0, nextSplit);
|
---|
599 | line = line.substring(nextSplit + 1);
|
---|
600 | } else {
|
---|
601 | System.err.println("ResultBox addDocumentTag: error parsing: " + line);
|
---|
602 | }
|
---|
603 | }
|
---|
604 |
|
---|
605 | // Read the document frequency
|
---|
606 | else if (line.startsWith("freq")) {
|
---|
607 | line = line.substring(6);
|
---|
608 | nextSplit = line.indexOf((int) '"');
|
---|
609 | if (nextSplit >= 1) {
|
---|
610 | freq = line.substring(0, nextSplit);
|
---|
611 | line = line.substring(nextSplit + 1);
|
---|
612 | } else {
|
---|
613 | System.err.println("ResultBox addDocumentTag: error parsing: " + line);
|
---|
614 | }
|
---|
615 | }
|
---|
616 |
|
---|
617 | // Read the title
|
---|
618 | else if (line.startsWith("title")) {
|
---|
619 | line = line.substring(7);
|
---|
620 | nextSplit = line.indexOf((int) '"');
|
---|
621 | if (nextSplit >= 1) {
|
---|
622 | title = line.substring(0, nextSplit);
|
---|
623 | line = line.substring(nextSplit + 1);
|
---|
624 | } else {
|
---|
625 | System.err.println("ResultBox addDocumentTag: error parsing: " + line);
|
---|
626 | }
|
---|
627 | }
|
---|
628 |
|
---|
629 | // Read some other tag or close the string off
|
---|
630 | else {
|
---|
631 | nextSplit = line.indexOf((int) ' ');
|
---|
632 | if (nextSplit >= 1) {
|
---|
633 | line = line.substring(nextSplit + 1);
|
---|
634 | } else {
|
---|
635 | line = "";
|
---|
636 | }
|
---|
637 | }
|
---|
638 | }
|
---|
639 |
|
---|
640 | // Create a new ResultItem and add it to the display
|
---|
641 | ResultItemDocument ri = new ResultItemDocument(hash, title, freq);
|
---|
642 |
|
---|
643 | if (c.addResultItem(ri)) {
|
---|
644 | documentsRetrieved++;
|
---|
645 | return true;
|
---|
646 | }
|
---|
647 |
|
---|
648 | return false;
|
---|
649 | }
|
---|
650 |
|
---|
651 |
|
---|
652 | // Add a thesaurus tag
|
---|
653 | //
|
---|
654 | // Given a string containing an XML document tag of the form:
|
---|
655 | //
|
---|
656 | // <thesaurus num="3" id="36506" tf="0" df="0" type="RT" text="ANGLOPHONE AFRICA"/>
|
---|
657 | // <thesaurus num="4" id="28724" tf="0" df="0" type="RT" text="FRANCOPHONE AFRICA"/>
|
---|
658 | //
|
---|
659 | // Create a new ResultItemLink for display
|
---|
660 | //
|
---|
661 | // Return true if successful, otherwise false.
|
---|
662 |
|
---|
663 | boolean addThesaurusTag( String line ) {
|
---|
664 |
|
---|
665 | // System.out.println( "addThesaurusTag: " + line + " (" + thesaurusLinksRetrieved + ")");
|
---|
666 |
|
---|
667 | String num = "", id = "", tf = "", df = "", type = "", text = "";
|
---|
668 | line = line.substring(10);
|
---|
669 |
|
---|
670 | // Break the tag down into its component parts
|
---|
671 | int nextSplit;
|
---|
672 | while (line.length() > 0) {
|
---|
673 | line = line.trim();
|
---|
674 |
|
---|
675 | // Read the expansion number
|
---|
676 | if (line.startsWith("num")) {
|
---|
677 | line = line.substring(5);
|
---|
678 | nextSplit = line.indexOf((int) '"');
|
---|
679 | if (nextSplit >= 1) {
|
---|
680 | num = line.substring(0, nextSplit);
|
---|
681 | line = line.substring(nextSplit + 1);
|
---|
682 | } else {
|
---|
683 | System.err.println("ResultBox addThesaurusTag: error parsing: " + line);
|
---|
684 | }
|
---|
685 | }
|
---|
686 |
|
---|
687 | // Read the phrase ID
|
---|
688 | else if (line.startsWith("id")) {
|
---|
689 | line = line.substring(4);
|
---|
690 | nextSplit = line.indexOf((int) '"');
|
---|
691 | if (nextSplit >= 1) {
|
---|
692 | id = line.substring(0, nextSplit);
|
---|
693 | line = line.substring(nextSplit + 1);
|
---|
694 | } else {
|
---|
695 | System.err.println("ResultBox addThesaurusTag: error parsing: " + line);
|
---|
696 | }
|
---|
697 | }
|
---|
698 |
|
---|
699 | // Read the phrase link type
|
---|
700 | else if (line.startsWith("type")) {
|
---|
701 | line = line.substring(6);
|
---|
702 | nextSplit = line.indexOf((int) '"');
|
---|
703 | if (nextSplit >= 1) {
|
---|
704 | type = line.substring(0, nextSplit);
|
---|
705 | line = line.substring(nextSplit + 1);
|
---|
706 | } else {
|
---|
707 | System.err.println("ResultBox addThesaurusTag: error parsing: " + line);
|
---|
708 | }
|
---|
709 | }
|
---|
710 |
|
---|
711 |
|
---|
712 | // Read the phrase text
|
---|
713 | else if (line.startsWith("text")) {
|
---|
714 | line = line.substring(6);
|
---|
715 | nextSplit = line.indexOf((int) '"');
|
---|
716 | if (nextSplit >= 1) {
|
---|
717 | text = line.substring(0, nextSplit);
|
---|
718 | line = line.substring(nextSplit + 1);
|
---|
719 | } else {
|
---|
720 | System.err.println("ResultBox addThesaurusTag: error parsing: " + line);
|
---|
721 | }
|
---|
722 | }
|
---|
723 |
|
---|
724 | // Read the frequency
|
---|
725 | else if (line.startsWith("tf")) {
|
---|
726 | line = line.substring(4);
|
---|
727 | nextSplit = line.indexOf((int) '"');
|
---|
728 | if (nextSplit >= 1) {
|
---|
729 | tf = line.substring(0, nextSplit);
|
---|
730 | line = line.substring(nextSplit + 1);
|
---|
731 | } else {
|
---|
732 | System.err.println("ResultBox addExpansionTag: error parsing: " + line);
|
---|
733 | }
|
---|
734 | }
|
---|
735 |
|
---|
736 | // Read the document frequency
|
---|
737 | else if (line.startsWith("df")) {
|
---|
738 | line = line.substring(4);
|
---|
739 | nextSplit = line.indexOf((int) '"');
|
---|
740 | if (nextSplit >= 1) {
|
---|
741 | df = line.substring(0, nextSplit);
|
---|
742 | line = line.substring(nextSplit + 1);
|
---|
743 | } else {
|
---|
744 | System.err.println("ResultBox addExpansionTag: error parsing: " + line);
|
---|
745 | }
|
---|
746 | }
|
---|
747 |
|
---|
748 |
|
---|
749 | // Read some other tag or close the string off
|
---|
750 | else {
|
---|
751 | nextSplit = line.indexOf((int) ' ');
|
---|
752 | if (nextSplit >= 1) {
|
---|
753 | line = line.substring(nextSplit + 1);
|
---|
754 | } else {
|
---|
755 | line = "";
|
---|
756 | }
|
---|
757 | }
|
---|
758 | }
|
---|
759 |
|
---|
760 | // Create a new ResultItem and add it to the display
|
---|
761 | ResultItemLink ri = new ResultItemLink(id, text, type, tf, df);
|
---|
762 |
|
---|
763 | if (c.addResultItem(ri)) {
|
---|
764 | thesaurusLinksRetrieved++;
|
---|
765 | return true;
|
---|
766 | }
|
---|
767 |
|
---|
768 | return false;
|
---|
769 | }
|
---|
770 | }
|
---|
771 |
|
---|
772 |
|
---|
773 |
|
---|
774 |
|
---|