root / tmp / org.txm.groovy.core / src / groovy / org / txm / scripts / importer / transcriber / pager.groovy @ 2369
History | View | Annotate | Download (26.9 kB)
| 1 |
// Copyright © 2010-2013 ENS de Lyon.
|
|---|---|
| 2 |
// Copyright © 2007-2010 ENS de Lyon, CNRS, INRP, University of
|
| 3 |
// Lyon 2, University of Franche-Comté, University of Nice
|
| 4 |
// Sophia Antipolis, University of Paris 3.
|
| 5 |
//
|
| 6 |
// The TXM platform is free software: you can redistribute it
|
| 7 |
// and/or modify it under the terms of the GNU General Public
|
| 8 |
// License as published by the Free Software Foundation,
|
| 9 |
// either version 2 of the License, or (at your option) any
|
| 10 |
// later version.
|
| 11 |
//
|
| 12 |
// The TXM platform is distributed in the hope that it will be
|
| 13 |
// useful, but WITHOUT ANY WARRANTY; without even the implied
|
| 14 |
// warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR
|
| 15 |
// PURPOSE. See the GNU General Public License for more
|
| 16 |
// details.
|
| 17 |
//
|
| 18 |
// You should have received a copy of the GNU General
|
| 19 |
// Public License along with the TXM platform. If not, see
|
| 20 |
// http://www.gnu.org/licenses.
|
| 21 |
//
|
| 22 |
//
|
| 23 |
//
|
| 24 |
// $LastChangedDate:$
|
| 25 |
// $LastChangedRevision:$
|
| 26 |
// $LastChangedBy:$
|
| 27 |
//
|
| 28 |
package org.txm.scripts.importer.transcriber
|
| 29 |
|
| 30 |
import java.io.File; |
| 31 |
import java.util.ArrayList; |
| 32 |
|
| 33 |
import javax.xml.stream.* |
| 34 |
|
| 35 |
import org.txm.importer.ApplyXsl2 |
| 36 |
import org.txm.metadatas.MetadataGroup |
| 37 |
import org.txm.metadatas.Metadatas |
| 38 |
import org.txm.utils.io.FileCopy; |
| 39 |
|
| 40 |
|
| 41 |
// TODO: Auto-generated Javadoc
|
| 42 |
/** Build Discours corpus simple edition from a xml-tei.
|
| 43 |
*
|
| 44 |
* @author mdecorde
|
| 45 |
*
|
| 46 |
*/
|
| 47 |
class pager { |
| 48 |
|
| 49 |
boolean SIMPLE_TOOLTIP = false; // show less properties in word tooltips |
| 50 |
String ENQ_HIGHLIGHT_ELEMENT = "b" |
| 51 |
|
| 52 |
List<String> NoSpaceBefore; |
| 53 |
|
| 54 |
/** The No space after. */
|
| 55 |
List<String> NoSpaceAfter; |
| 56 |
|
| 57 |
/** The pages. */
|
| 58 |
def pages = []; |
| 59 |
def indexes = []; |
| 60 |
|
| 61 |
/** The wordcount. */
|
| 62 |
int wordcount = 0; |
| 63 |
|
| 64 |
/** The pagecount. */
|
| 65 |
int pagecount = 0; |
| 66 |
|
| 67 |
/** The wordmax. */
|
| 68 |
int wordmax = 10; |
| 69 |
|
| 70 |
/** The wordid. */
|
| 71 |
String wordid;
|
| 72 |
|
| 73 |
/** The first word. */
|
| 74 |
boolean firstWord = true; |
| 75 |
|
| 76 |
/** The wordvalue. */
|
| 77 |
String wordvalue;
|
| 78 |
|
| 79 |
/** The interpvalue. */
|
| 80 |
String interpvalue;
|
| 81 |
|
| 82 |
/** The lastword. */
|
| 83 |
String lastword = " "; |
| 84 |
|
| 85 |
/** The wordtype. */
|
| 86 |
String wordtype;
|
| 87 |
|
| 88 |
/** The flagform. */
|
| 89 |
boolean flagform = false; |
| 90 |
|
| 91 |
/** The flaginterp. */
|
| 92 |
boolean flaginterp = false; |
| 93 |
|
| 94 |
boolean flagcomment = false; |
| 95 |
|
| 96 |
/** The url. */
|
| 97 |
private def url; |
| 98 |
|
| 99 |
/** The input data. */
|
| 100 |
private def inputData; |
| 101 |
|
| 102 |
/** The factory. */
|
| 103 |
private def factory; |
| 104 |
|
| 105 |
/** The parser. */
|
| 106 |
private XMLStreamReader parser;
|
| 107 |
|
| 108 |
/** The writer. */
|
| 109 |
XMLStreamWriter writer; |
| 110 |
BufferedOutputStream output;
|
| 111 |
|
| 112 |
File txmfile;
|
| 113 |
|
| 114 |
File outfile;
|
| 115 |
|
| 116 |
String corpusname =""; |
| 117 |
String cuttingTag = "pb" |
| 118 |
String txtname;
|
| 119 |
File htmlDir;
|
| 120 |
File defaultDir;
|
| 121 |
Metadatas metadatas; |
| 122 |
|
| 123 |
def interviewers = []; |
| 124 |
def eventTranslations = ["^^":"mot inconnu", "?":"orthographe incertaine", |
| 125 |
"()":"rupture de syntaxe", "b":"bruit indéterminé", |
| 126 |
"*":"mot corrigé", |
| 127 |
"bb":"bruit de bouche", "bg":"bruit de gorge", |
| 128 |
"ch":"voix chuchotée", "conv":"conversations de fond", |
| 129 |
"e":"expiration", "i":"inspiration", |
| 130 |
"mic":"bruits micro", "n":"reniflement", |
| 131 |
"nontrant":"non transcrit", "pap":"froissement de papiers", |
| 132 |
"pf":"souffle", "pi":"inintelligible", |
| 133 |
"pif":"inaudible", "r":"respiration", |
| 134 |
"rire":"rire du locuteur", "shh":"soufle électrique", |
| 135 |
"sif":"sifflement du locuteur", "tx":"toux"]; |
| 136 |
String currentTime = ""; |
| 137 |
boolean bold = false; |
| 138 |
int writenLength = 0; |
| 139 |
boolean spokenTurn = false; |
| 140 |
boolean firstSync = false; |
| 141 |
boolean firstWho = false; |
| 142 |
/**
|
| 143 |
* Instantiates a new pager.
|
| 144 |
*
|
| 145 |
* @param infile the infile
|
| 146 |
* @param outfile the outfile
|
| 147 |
* @param NoSpaceBefore the no space before
|
| 148 |
* @param NoSpaceAfter the no space after
|
| 149 |
* @param max the max
|
| 150 |
* @param metadatas the metadatas
|
| 151 |
*/
|
| 152 |
pager(File txmfile, File htmlDir, String txtname, List<String> NoSpaceBefore, |
| 153 |
List<String> NoSpaceAfter, int max, String corpusname, String cuttingTag, Metadatas metadatas) { |
| 154 |
this.metadatas = metadatas
|
| 155 |
this.wordmax = max;
|
| 156 |
this.cuttingTag = cuttingTag;
|
| 157 |
this.corpusname = corpusname;
|
| 158 |
this.NoSpaceBefore = NoSpaceBefore;
|
| 159 |
this.NoSpaceAfter = NoSpaceAfter;
|
| 160 |
this.url = txmfile.toURI().toURL();
|
| 161 |
this.txmfile = txmfile;
|
| 162 |
this.htmlDir = htmlDir;
|
| 163 |
this.txtname = txtname;
|
| 164 |
|
| 165 |
inputData = url.openStream(); |
| 166 |
factory = XMLInputFactory.newInstance(); |
| 167 |
parser = factory.createXMLStreamReader(inputData); |
| 168 |
|
| 169 |
defaultDir = new File(htmlDir, "default") |
| 170 |
defaultDir.mkdir() |
| 171 |
new File(htmlDir, "onepage").mkdir() |
| 172 |
outfile = new File(htmlDir, "onepage/${txtname}.html"); |
| 173 |
createOutput(outfile) |
| 174 |
|
| 175 |
try {
|
| 176 |
process(); |
| 177 |
} catch(Exception e) { |
| 178 |
org.txm.utils.logger.Log.printStackTrace(e); |
| 179 |
if (writer != null) { |
| 180 |
writer.close(); |
| 181 |
output.close(); |
| 182 |
} |
| 183 |
} |
| 184 |
} |
| 185 |
|
| 186 |
/**
|
| 187 |
* Creates the output.
|
| 188 |
*
|
| 189 |
* @param outfile the outfile
|
| 190 |
* @return true, if successful
|
| 191 |
*/
|
| 192 |
private boolean createOutput(File outfile) { |
| 193 |
try {
|
| 194 |
//println "write html in : "+outfile
|
| 195 |
XMLOutputFactory outfactory = XMLOutputFactory.newInstance(); |
| 196 |
output = new BufferedOutputStream(new FileOutputStream(outfile)) |
| 197 |
writer = outfactory.createXMLStreamWriter(output, "UTF-8");//create a new file |
| 198 |
|
| 199 |
return true; |
| 200 |
} catch (Exception e) { |
| 201 |
System.out.println(e.getLocalizedMessage());
|
| 202 |
return false; |
| 203 |
} |
| 204 |
} |
| 205 |
|
| 206 |
/** The events. */
|
| 207 |
List<String> events = []; |
| 208 |
String previousEvent = "", nextEvent = ""; |
| 209 |
/**
|
| 210 |
* Process.
|
| 211 |
*/
|
| 212 |
void process() {
|
| 213 |
|
| 214 |
String previousElem = ""; |
| 215 |
boolean parolesRaportees = false; |
| 216 |
boolean firstWord = true; |
| 217 |
boolean shouldBreak = false; |
| 218 |
boolean overlapping = false; |
| 219 |
int nbBreak = 0; |
| 220 |
String previousSPK;
|
| 221 |
String localname = ""; |
| 222 |
ArrayList<String> whos = []; |
| 223 |
HashMap<String, String> speakers = new HashMap<String, String>(); |
| 224 |
HashMap<String, String> topics = new HashMap<String, String>(); |
| 225 |
|
| 226 |
writer.writeStartDocument("UTF-8","1.0"); |
| 227 |
writer.writeStartElement("html");
|
| 228 |
//<meta http-equiv="Content-Type" content="text/html; charset=UTF-8"/>
|
| 229 |
writer.writeStartElement("meta");
|
| 230 |
writer.writeAttribute("http-equiv", "Content-Type"); |
| 231 |
writer.writeAttribute("content", "text/html"); |
| 232 |
writer.writeAttribute("charset", "UTF-8"); |
| 233 |
writer.writeEndElement(); // meta
|
| 234 |
writer.writeStartElement("head");
|
| 235 |
//<link rel="stylesheet" type="text/css" href="class.css" />
|
| 236 |
writer.writeStartElement("link");
|
| 237 |
writer.writeAttribute("rel", "stylesheet"); |
| 238 |
writer.writeAttribute("type", "text/css"); |
| 239 |
writer.writeAttribute("href", "transcriber.css"); |
| 240 |
writer.writeEndElement(); // link
|
| 241 |
writer.writeStartElement("link");
|
| 242 |
writer.writeAttribute("rel", "stylesheet"); |
| 243 |
writer.writeAttribute("type", "text/css"); |
| 244 |
writer.writeAttribute("href", corpusname+".css"); |
| 245 |
writer.writeEndElement(); // link
|
| 246 |
writer.writeEndElement(); // head
|
| 247 |
|
| 248 |
nbBreak++ |
| 249 |
writer.writeStartElement("body");
|
| 250 |
writer.writeAttribute("class", "txmeditionpage") |
| 251 |
writer.writeEmptyElement("pb");
|
| 252 |
writer.writeAttribute("id", ""+nbBreak); |
| 253 |
pages << new File(defaultDir, "${txtname}_${nbBreak}.html") |
| 254 |
|
| 255 |
for (int event = parser.next(); event != XMLStreamConstants.END_DOCUMENT; event = parser.next()) { |
| 256 |
switch (event) {
|
| 257 |
case XMLStreamConstants.START_ELEMENT:
|
| 258 |
localname = parser.getLocalName(); |
| 259 |
switch (localname) {
|
| 260 |
case "text": |
| 261 |
|
| 262 |
writer.writeStartElement("h1");
|
| 263 |
writer.writeAttribute("class", "title"); |
| 264 |
String title = parser.getAttributeValue(null, "title"); |
| 265 |
|
| 266 |
if (title != null) { |
| 267 |
writer.writeCharacters(title); |
| 268 |
} else {
|
| 269 |
writer.writeCharacters("Transcription "+txmfile.getName().substring(0, txmfile.getName().length() - 4)); |
| 270 |
} |
| 271 |
|
| 272 |
writeMediaAccess("0.0")
|
| 273 |
|
| 274 |
writer.writeEndElement(); // h1
|
| 275 |
|
| 276 |
String subtitle = parser.getAttributeValue(null, "subtitle"); |
| 277 |
if (subtitle != null && subtitle.length() > 0) { |
| 278 |
writer.writeStartElement("h2");
|
| 279 |
writer.writeAttribute("class", "subtitle"); |
| 280 |
writer.writeCharacters(subtitle); |
| 281 |
writer.writeEndElement(); // h2
|
| 282 |
} |
| 283 |
|
| 284 |
writer.writeStartElement("table");
|
| 285 |
writer.writeAttribute("class", "transcription-table"); |
| 286 |
boolean grey = false; |
| 287 |
for (int i = 0 ; i < parser.getAttributeCount() ; i++) { |
| 288 |
String name = parser.getAttributeName(i);
|
| 289 |
String value = parser.getAttributeValue(i);
|
| 290 |
|
| 291 |
if ("title" == name) { |
| 292 |
continue; // ignore "title" metadata |
| 293 |
} |
| 294 |
|
| 295 |
grey = !grey; |
| 296 |
writer.writeStartElement("tr");
|
| 297 |
if (grey) {
|
| 298 |
writer.writeAttribute("style","background-color:lightgrey;") |
| 299 |
} |
| 300 |
|
| 301 |
if (value != null) { |
| 302 |
writer.writeStartElement("td");
|
| 303 |
writer.writeCharacters(name); |
| 304 |
writer.writeEndElement(); // td
|
| 305 |
writer.writeStartElement("td");
|
| 306 |
writer.writeCharacters(value); |
| 307 |
writer.writeEndElement(); // td
|
| 308 |
} |
| 309 |
//get enqueteur to style their names
|
| 310 |
if (name.startsWith("enq")) { |
| 311 |
interviewers.add(value) |
| 312 |
} |
| 313 |
writer.writeEndElement(); // tr
|
| 314 |
} |
| 315 |
writer.writeEndElement(); // table
|
| 316 |
// }
|
| 317 |
break;
|
| 318 |
case "Topics": |
| 319 |
/*writer.writeStartElement("h2");
|
| 320 |
writer.writeCharacters("Topics");
|
| 321 |
writer.writeEndElement();
|
| 322 |
writer.writeStartElement("ul");
|
| 323 |
*/
|
| 324 |
break;
|
| 325 |
case "Topic": |
| 326 |
topics.put(parser.getAttributeValue(null,"id"), parser.getAttributeValue(null,"desc")) |
| 327 |
/*writer.writeStartElement("li");
|
| 328 |
writer.writeCharacters(parser.getAttributeValue(null,"desc"));
|
| 329 |
writer.writeStartElement("ul");
|
| 330 |
for(int i = 0 ; i < parser.getAttributeCount() ; i++)
|
| 331 |
{
|
| 332 |
if(parser.getAttributeLocalName(i) != "desc")
|
| 333 |
{
|
| 334 |
writer.writeStartElement("li");
|
| 335 |
writer.writeCharacters(parser.getAttributeLocalName(i)+": "+parser.getAttributeValue(i));
|
| 336 |
writer.writeEndElement();
|
| 337 |
}
|
| 338 |
}
|
| 339 |
writer.writeEndElement();
|
| 340 |
writer.writeEndElement();
|
| 341 |
*/
|
| 342 |
break;
|
| 343 |
case "Speakers": |
| 344 |
/*writer.writeStartElement("h2");
|
| 345 |
writer.writeCharacters("Speakers");
|
| 346 |
writer.writeEndElement();
|
| 347 |
writer.writeStartElement("ul");*/
|
| 348 |
break;
|
| 349 |
case "Speaker": |
| 350 |
whos.add(parser.getAttributeValue(null,"name")); |
| 351 |
speakers.put(parser.getAttributeValue(null,"id"), parser.getAttributeValue(null,"name")) |
| 352 |
/*writer.writeStartElement("li");
|
| 353 |
writer.writeStartElement("ul");
|
| 354 |
writer.writeCharacters(parser.getAttributeValue(null,"name"));
|
| 355 |
for(int i = 0 ; i < parser.getAttributeCount() ; i++)
|
| 356 |
{
|
| 357 |
if(parser.getAttributeLocalName(i) != "name")
|
| 358 |
{
|
| 359 |
writer.writeStartElement("li");
|
| 360 |
writer.writeCharacters(parser.getAttributeLocalName(i)+": "+parser.getAttributeValue(i));
|
| 361 |
writer.writeEndElement();
|
| 362 |
}
|
| 363 |
}
|
| 364 |
writer.writeEndElement();
|
| 365 |
writer.writeEndElement();*/
|
| 366 |
break;
|
| 367 |
case "Comment": |
| 368 |
spokenTurn = true;
|
| 369 |
writenLength++; |
| 370 |
writer.writeStartElement("span");
|
| 371 |
writer.writeAttribute("class", "comment"); |
| 372 |
writer.writeCharacters(" ["+parser.getAttributeValue(0)+"] "); |
| 373 |
writer.writeEndElement(); |
| 374 |
flagcomment = true;
|
| 375 |
break;
|
| 376 |
case "div": |
| 377 |
|
| 378 |
nbBreak++ |
| 379 |
writer.writeEmptyElement("pb");
|
| 380 |
writer.writeAttribute("id", ""+nbBreak); |
| 381 |
writer.writeCharacters("\n");
|
| 382 |
|
| 383 |
pages << new File(defaultDir, "${txtname}_${nbBreak}.html") |
| 384 |
indexes << wordid |
| 385 |
|
| 386 |
wordcount = 0;
|
| 387 |
shouldBreak = false;
|
| 388 |
|
| 389 |
writer.writeStartElement("div")
|
| 390 |
writer.writeAttribute("class", "section") |
| 391 |
|
| 392 |
String type = parser.getAttributeValue(null, "type") |
| 393 |
writer.writeAttribute("type", ""+type) |
| 394 |
|
| 395 |
String desc = parser.getAttributeValue(null, "topic") |
| 396 |
|
| 397 |
if (type != null && type.length() > 0) { |
| 398 |
writer.writeStartElement("h2");
|
| 399 |
writer.writeAttribute("class", "section-title") |
| 400 |
writer.writeCharacters(type); |
| 401 |
|
| 402 |
if (parser.getAttributeValue(null,"startTime") != null) { |
| 403 |
writeMediaAccess(parser.getAttributeValue(null,"startTime")) |
| 404 |
} |
| 405 |
|
| 406 |
writer.writeEndElement(); // h1
|
| 407 |
} |
| 408 |
|
| 409 |
if (desc != null && desc.length() > 0) { |
| 410 |
writer.writeStartElement("h2");
|
| 411 |
writer.writeAttribute("class", "section-desc") |
| 412 |
writer.writeCharacters(desc) |
| 413 |
writer.writeEndElement(); // h2
|
| 414 |
} |
| 415 |
|
| 416 |
def metadata = new LinkedHashMap<String, String>() // temp to store attributes |
| 417 |
def metadataGroups = ["metadata":[]] // default metadata group |
| 418 |
def metadataDeclared = false |
| 419 |
if (parser.getAttributeValue(null, "metadata") != null && parser.getAttributeValue(null, "metadata_groups") != null) { |
| 420 |
def l1 = parser.getAttributeValue(null, "metadata").split("\\|"); |
| 421 |
def l2 = parser.getAttributeValue(null, "metadata_groups").split("\\|"); |
| 422 |
for (int i = 0 ; i < l1.size() ; i++) { |
| 423 |
def m = l1[i]
|
| 424 |
def g = l2[i]
|
| 425 |
metadata[m] = "" // forcing order of metadata by pre-declaring |
| 426 |
if (!metadataGroups.containsKey(g)) metadataGroups[g] = [] |
| 427 |
metadataGroups[g] << m // declaring a metadata type
|
| 428 |
} |
| 429 |
metadataDeclared = true
|
| 430 |
} |
| 431 |
|
| 432 |
for (int i = 0 ; i < parser.getAttributeCount() ; i++) { |
| 433 |
String name = parser.getAttributeLocalName(i)
|
| 434 |
if (!"type".equals(name) |
| 435 |
&& !"topic".equals(name)
|
| 436 |
&& !"startTime".equals(name)
|
| 437 |
&& !"endTime".equals(name)) {
|
| 438 |
if (metadataDeclared && !metadata.containsKey(name)) {
|
| 439 |
continue; // ignoring metadata since not in declared metadata |
| 440 |
} else {
|
| 441 |
metadataGroups["metadata"] << name
|
| 442 |
} |
| 443 |
|
| 444 |
metadata[name] = parser.getAttributeValue(i) |
| 445 |
} |
| 446 |
} |
| 447 |
|
| 448 |
if (metadataGroups.keySet().size() > 0) { |
| 449 |
writer.writeStartElement("p")
|
| 450 |
writer.writeAttribute("class", "section-all-metadata"); |
| 451 |
for (String groupName : metadataGroups.keySet()) { |
| 452 |
def group = metadataGroups[groupName]
|
| 453 |
if (group.size() > 0) { |
| 454 |
if (groupName.equals("text")) { |
| 455 |
writer.writeStartElement("p")
|
| 456 |
writer.writeAttribute("class", "section-"+groupName); |
| 457 |
for (String k : group) { |
| 458 |
writer.writeStartElement("p")
|
| 459 |
writer.writeAttribute("class", ""+groupName) |
| 460 |
writer.writeStartElement("h4")
|
| 461 |
writer.writeCharacters(k) |
| 462 |
writer.writeEndElement() // h4
|
| 463 |
writer.writeCharacters(metadata[k]) |
| 464 |
writer.writeEndElement() // p
|
| 465 |
} |
| 466 |
} else {
|
| 467 |
writer.writeStartElement("ul")
|
| 468 |
writer.writeAttribute("class", "section-"+groupName); |
| 469 |
for (String k : group) { |
| 470 |
writer.writeStartElement("li")
|
| 471 |
writer.writeAttribute("class", ""+groupName) |
| 472 |
writer.writeCharacters(""+k+": "+metadata[k]) |
| 473 |
writer.writeEndElement() // li
|
| 474 |
} |
| 475 |
} |
| 476 |
|
| 477 |
writer.writeEndElement(); // ul or p
|
| 478 |
} |
| 479 |
} |
| 480 |
writer.writeEndElement(); // p
|
| 481 |
writer.writeEmptyElement("hr")
|
| 482 |
} |
| 483 |
|
| 484 |
break;
|
| 485 |
case "sp": |
| 486 |
endBoldIfNeeded() |
| 487 |
firstSync = true;
|
| 488 |
firstWho = true;
|
| 489 |
spokenTurn = false;
|
| 490 |
overlapping = false
|
| 491 |
|
| 492 |
writer.writeStartElement("p");
|
| 493 |
writer.writeAttribute("class", "turn"); |
| 494 |
|
| 495 |
overlapping = ("true" == parser.getAttributeValue(null,"overlap")) |
| 496 |
String spid = parser.getAttributeValue(null,"speaker"); |
| 497 |
|
| 498 |
whos = []
|
| 499 |
if (overlapping) {
|
| 500 |
writer.writeEmptyElement("br");
|
| 501 |
writeSpeaker(parser.getAttributeValue(null,"speaker"), false) |
| 502 |
|
| 503 |
writer.writeEmptyElement("br");
|
| 504 |
whos = spid.split(" ")
|
| 505 |
} |
| 506 |
|
| 507 |
break;
|
| 508 |
case "u": |
| 509 |
writer.writeCharacters("\n");
|
| 510 |
this.currentTime = parser.getAttributeValue(null,"time"); |
| 511 |
|
| 512 |
if (previousElem == "u" && writenLength == 0) { // if previous u had no words, it was a silence |
| 513 |
writer.writeStartElement("span");
|
| 514 |
writer.writeAttribute("class", "event"); |
| 515 |
writer.writeCharacters("[silence]");
|
| 516 |
writer.writeEndElement(); // span
|
| 517 |
writer.writeEmptyElement("br");
|
| 518 |
} |
| 519 |
|
| 520 |
String spk = parser.getAttributeValue(null, "spk") |
| 521 |
if (spk != null && spk != previousSPK) { |
| 522 |
endBoldIfNeeded() |
| 523 |
writer.writeEmptyElement("br");
|
| 524 |
writeSpeaker(parser.getAttributeValue(null, "spk"), overlapping) |
| 525 |
startBoldIfNeeded() |
| 526 |
} |
| 527 |
|
| 528 |
writeCurrentTime() |
| 529 |
previousSPK = spk |
| 530 |
|
| 531 |
// writenLength = 0;
|
| 532 |
/*writer.writeStartElement("span");
|
| 533 |
writer.writeAttribute("class", "sync");
|
| 534 |
writer.writeCharacters("["+parser.getAttributeValue(null,"time")+"]");
|
| 535 |
writer.writeEndElement();*/
|
| 536 |
|
| 537 |
break;
|
| 538 |
case "event": |
| 539 |
spokenTurn = true;
|
| 540 |
writenLength++; |
| 541 |
String desc = parser.getAttributeValue(null,"desc"); |
| 542 |
desc = translateEvent(desc); |
| 543 |
String type = parser.getAttributeValue(null,"type"); |
| 544 |
if (desc.equals("paroles rapportées")) { |
| 545 |
if (parser.getAttributeValue(null, "extent") == "end") |
| 546 |
writer.writeCharacters("» ");
|
| 547 |
else if (parser.getAttributeValue(null, "extent") == "begin") |
| 548 |
writer.writeCharacters(" «");
|
| 549 |
} else {
|
| 550 |
writer.writeStartElement("span");
|
| 551 |
writer.writeAttribute("class", "event"); |
| 552 |
if (parser.getAttributeValue(null, "extent") == "end") { |
| 553 |
writer.writeCharacters(" <"+desc+"] "); |
| 554 |
if(events.size() > 0) |
| 555 |
events.remove(events.size()-1)
|
| 556 |
} |
| 557 |
else if (parser.getAttributeValue(null, "extent") == "begin") { |
| 558 |
|
| 559 |
writer.writeCharacters(" ["+desc+"> "); |
| 560 |
events.add(desc) |
| 561 |
} |
| 562 |
else if (parser.getAttributeValue(null, "extent") == "previous") { |
| 563 |
if(parser.getAttributeValue(null, "type") == "pronounce") |
| 564 |
writer.writeCharacters("_["+desc+"] "); |
| 565 |
else
|
| 566 |
writer.writeCharacters("_["+desc+"] "); |
| 567 |
previousEvent = desc; |
| 568 |
} |
| 569 |
else if (parser.getAttributeValue(null, "extent") == "next") { |
| 570 |
writer.writeCharacters(" ["+desc+"]_"); |
| 571 |
nextEvent = desc |
| 572 |
} |
| 573 |
else
|
| 574 |
writer.writeCharacters(" ["+desc+"] "); |
| 575 |
writer.writeEndElement(); // span@class=event
|
| 576 |
} |
| 577 |
break;
|
| 578 |
case "w": |
| 579 |
for(int i = 0 ; i < parser.getAttributeCount() ; i++) |
| 580 |
if(parser.getAttributeLocalName(i) == "id") { |
| 581 |
wordid = (parser.getAttributeValue(i)); |
| 582 |
break;
|
| 583 |
} |
| 584 |
|
| 585 |
wordcount++; |
| 586 |
if (wordcount >= wordmax) {
|
| 587 |
shouldBreak = true;
|
| 588 |
} |
| 589 |
|
| 590 |
if (firstWord) {
|
| 591 |
indexes << wordid |
| 592 |
firstWord = false;
|
| 593 |
} |
| 594 |
|
| 595 |
break;
|
| 596 |
|
| 597 |
case "ana": |
| 598 |
|
| 599 |
String type = parser.getAttributeValue(null,"type").substring(1); |
| 600 |
if (SIMPLE_TOOLTIP) {
|
| 601 |
if (type.contains("lemma") || type.contains("pos")) { |
| 602 |
flaginterp=true;
|
| 603 |
interpvalue+=", ";
|
| 604 |
} |
| 605 |
} else {
|
| 606 |
flaginterp=true;
|
| 607 |
interpvalue+=", "+type+"=" |
| 608 |
} |
| 609 |
break;
|
| 610 |
|
| 611 |
case "form": |
| 612 |
wordvalue="";
|
| 613 |
interpvalue ="";
|
| 614 |
flagform=true;
|
| 615 |
break;
|
| 616 |
} |
| 617 |
previousElem = localname; |
| 618 |
break;
|
| 619 |
|
| 620 |
case XMLStreamConstants.END_ELEMENT:
|
| 621 |
localname = parser.getLocalName(); |
| 622 |
switch(localname) {
|
| 623 |
case "text": |
| 624 |
break;
|
| 625 |
case "Topics": |
| 626 |
//writer.writeEndElement();
|
| 627 |
break;
|
| 628 |
case "Topic": |
| 629 |
break;
|
| 630 |
case "Speakers": |
| 631 |
//println "Speakers: "+speakers
|
| 632 |
//writer.writeEndElement();
|
| 633 |
break;
|
| 634 |
case "Speaker": |
| 635 |
break;
|
| 636 |
|
| 637 |
case "div": |
| 638 |
//writer.writeCharacters("}");
|
| 639 |
|
| 640 |
writer.writeEndElement(); // div
|
| 641 |
writer.writeCharacters("\n");
|
| 642 |
break;
|
| 643 |
case "sp": |
| 644 |
//println "CLOSING: "+parser.getLocalName()
|
| 645 |
endBoldIfNeeded() |
| 646 |
if (!spokenTurn) {
|
| 647 |
writer.writeStartElement("span");
|
| 648 |
writer.writeAttribute("class", "event"); |
| 649 |
writer.writeCharacters("[silence]");
|
| 650 |
writer.writeEndElement(); |
| 651 |
writer.writeEmptyElement("br");
|
| 652 |
} |
| 653 |
|
| 654 |
writer.writeEndElement(); // p
|
| 655 |
|
| 656 |
if (shouldBreak) {
|
| 657 |
nbBreak++ |
| 658 |
writer.writeEmptyElement("pb");
|
| 659 |
writer.writeAttribute("id", ""+nbBreak); |
| 660 |
writer.writeCharacters("\n");
|
| 661 |
|
| 662 |
pages << new File(defaultDir, "${txtname}_${nbBreak}.html") |
| 663 |
indexes << wordid |
| 664 |
|
| 665 |
wordcount = 0;
|
| 666 |
shouldBreak = false;
|
| 667 |
} |
| 668 |
writer.writeCharacters("\n");
|
| 669 |
break;
|
| 670 |
case "u": |
| 671 |
//writer.writeEndElement() // span@class=u
|
| 672 |
//writer.writeEmptyElement("br");
|
| 673 |
//if (overlapping) writer.writeEndElement(); // b
|
| 674 |
break;
|
| 675 |
case "event": |
| 676 |
break;
|
| 677 |
case "form": |
| 678 |
flagform = false
|
| 679 |
break;
|
| 680 |
case "ana": |
| 681 |
flaginterp = false
|
| 682 |
break;
|
| 683 |
case "w": |
| 684 |
writenLength++; |
| 685 |
spokenTurn = true;
|
| 686 |
int l = lastword.length();
|
| 687 |
String endOfLastWord = ""; |
| 688 |
if(l > 0) |
| 689 |
endOfLastWord = lastword.subSequence(l-1, l);
|
| 690 |
|
| 691 |
if(interpvalue != null) |
| 692 |
interpvalue = interpvalue.replace("\"","""); |
| 693 |
if(events.size() > 0) |
| 694 |
interpvalue = interpvalue.replace("event=", "event="+events.toString().replace("\"",""")); // remove ", " |
| 695 |
|
| 696 |
if(nextEvent.length() > 0) |
| 697 |
{
|
| 698 |
interpvalue = interpvalue.replace("event=", "event="+nextEvent+", ") |
| 699 |
nextEvent = ""
|
| 700 |
} |
| 701 |
interpvalue = interpvalue.replace("=, ","='', "); // add '' to empty interp value |
| 702 |
if (interpvalue.startsWith(", ")) interpvalue = interpvalue.substring(2) |
| 703 |
// println "** SPACE TEST"
|
| 704 |
// println "NoSpaceBefore: "+NoSpaceBefore+" contains ? "+wordvalue
|
| 705 |
// println "NoSpaceAfter: "+NoSpaceAfter+" contains ? "+lastword
|
| 706 |
// println "wordvalue starts with '-' ? "+wordvalue
|
| 707 |
// println "NoSpaceAfter: "+NoSpaceAfter+" contains endOfLastWord ? "+endOfLastWord
|
| 708 |
if(NoSpaceBefore.contains(wordvalue) ||
|
| 709 |
NoSpaceAfter.contains(lastword) || |
| 710 |
wordvalue.startsWith("-") ||
|
| 711 |
NoSpaceAfter.contains(endOfLastWord)) {
|
| 712 |
// println " NO SPACE"
|
| 713 |
} else {
|
| 714 |
// println " SPACE"
|
| 715 |
writer.writeCharacters(" ");
|
| 716 |
} |
| 717 |
|
| 718 |
if (interpvalue.contains("rapp1")) { |
| 719 |
writer.writeCharacters(" «");
|
| 720 |
} else if (wordvalue == "\"") { |
| 721 |
// don't write this char
|
| 722 |
} else {
|
| 723 |
writer.writeStartElement("span");
|
| 724 |
writer.writeAttribute("class", "word"); |
| 725 |
writer.writeAttribute("title", interpvalue);
|
| 726 |
writer.writeAttribute("id", wordid);
|
| 727 |
writer.writeCharacters(wordvalue); |
| 728 |
writer.writeEndElement(); |
| 729 |
} |
| 730 |
if (interpvalue.contains("orth")) { |
| 731 |
writer.writeStartElement("span");
|
| 732 |
writer.writeAttribute("class", "event"); |
| 733 |
writer.writeCharacters("_[?]");
|
| 734 |
writer.writeEndElement(); |
| 735 |
} |
| 736 |
if (interpvalue.contains("corr")) { |
| 737 |
writer.writeStartElement("span");
|
| 738 |
writer.writeAttribute("class", "event"); |
| 739 |
writer.writeCharacters("_[!]");
|
| 740 |
writer.writeEndElement(); |
| 741 |
} |
| 742 |
|
| 743 |
if (interpvalue.contains("rapp2")) { |
| 744 |
writer.writeCharacters(" » ");
|
| 745 |
} |
| 746 |
|
| 747 |
lastword=wordvalue; |
| 748 |
break;
|
| 749 |
} |
| 750 |
|
| 751 |
break;
|
| 752 |
|
| 753 |
case XMLStreamConstants.CHARACTERS:
|
| 754 |
if(flagform)
|
| 755 |
if(parser.getText().length() > 0) |
| 756 |
wordvalue+=(parser.getText().trim()); |
| 757 |
if(flaginterp)
|
| 758 |
if(parser.getText().length() > 0) |
| 759 |
interpvalue+=(parser.getText().trim()); |
| 760 |
break;
|
| 761 |
} |
| 762 |
} |
| 763 |
writer.writeEndElement(); // body
|
| 764 |
|
| 765 |
writer.writeEmptyElement("pb");
|
| 766 |
nbBreak++ |
| 767 |
writer.writeAttribute("id", ""+nbBreak); |
| 768 |
|
| 769 |
writer.writeEndElement(); // html
|
| 770 |
writer.close(); |
| 771 |
output.close(); |
| 772 |
if (parser != null) parser.close(); |
| 773 |
if (inputData != null) inputData.close(); |
| 774 |
|
| 775 |
File txmhome = new File(org.txm.Toolbox.getTxmHomePath()); |
| 776 |
File xlsDir = new File(txmhome, "xsl"); |
| 777 |
File xslfile = new File(xlsDir,"breakByMilestone.xsl"); |
| 778 |
if (!xslfile.exists()) {
|
| 779 |
println ""
|
| 780 |
} |
| 781 |
// println "xsl: "+xslfile
|
| 782 |
// println "html: "+outfile
|
| 783 |
// println "pages: "+pages
|
| 784 |
// println "words: "+indexes
|
| 785 |
|
| 786 |
|
| 787 |
if (pages.size() > 1) { |
| 788 |
for (int i = 1 ; i < nbBreak ; i++) { |
| 789 |
ApplyXsl2 a = new ApplyXsl2(xslfile.getAbsolutePath());
|
| 790 |
String[] params = ["pbval1", i, "pbval2", i+1]; |
| 791 |
|
| 792 |
File resultfile = pages[i-1] |
| 793 |
//println "BBmilestones: "+i+" "+(i+1)+" in file "+resultfile
|
| 794 |
//println "process $outfile -> $resultfile"
|
| 795 |
a.process(outfile.getAbsolutePath(), resultfile.getAbsolutePath(), params); |
| 796 |
} |
| 797 |
} else {
|
| 798 |
File page = pages[0] |
| 799 |
FileCopy.copy(outfile, page) |
| 800 |
} |
| 801 |
outfile.delete() // onepage edition -> no more needed
|
| 802 |
} |
| 803 |
|
| 804 |
private void writeCurrentTime() { |
| 805 |
writer.writeStartElement("span");
|
| 806 |
writer.writeAttribute("class", "sync"); |
| 807 |
writer.writeCharacters(currentTime); |
| 808 |
|
| 809 |
writeMediaAccess(currentTime) |
| 810 |
|
| 811 |
writer.writeEndElement() // span
|
| 812 |
} |
| 813 |
|
| 814 |
private void writeMediaAccess(def time) { |
| 815 |
writer.writeCharacters(" ");
|
| 816 |
writer.writeStartElement("a");
|
| 817 |
writer.writeAttribute("onclick", "txmcommand('id', 'org.txm.backtomedia.commands.function.BackToMedia', 'corpus', '"+corpusname+"', 'text', '"+txtname+"', 'time', '"+time+"')"); |
| 818 |
writer.writeAttribute("style", "cursor: pointer;") |
| 819 |
writer.writeAttribute("class", "play-media") |
| 820 |
writer.writeCharacters("♫");
|
| 821 |
writer.writeEndElement(); // a
|
| 822 |
} |
| 823 |
|
| 824 |
private void writeSpeaker(String spk, boolean overlapping) { |
| 825 |
|
| 826 |
writer.writeStartElement("span");
|
| 827 |
writer.writeAttribute("class", "spk"); |
| 828 |
if(interviewers.contains(spk))
|
| 829 |
bold = true;
|
| 830 |
else
|
| 831 |
bold = false;
|
| 832 |
spk = spk.replaceAll('^([^0-9]*)([0-9]+)$', '$1 $2'); |
| 833 |
if (overlapping) writer.writeCharacters("// ") |
| 834 |
|
| 835 |
writer.writeCharacters(spk+": ")
|
| 836 |
|
| 837 |
writer.writeEndElement(); // span@class=spk
|
| 838 |
} |
| 839 |
|
| 840 |
private String translateEvent(String desc) { |
| 841 |
if(eventTranslations.containsKey(desc))
|
| 842 |
return eventTranslations.get(desc);
|
| 843 |
else
|
| 844 |
return desc;
|
| 845 |
} |
| 846 |
|
| 847 |
boolean boldOpenned = false; |
| 848 |
private void startBoldIfNeeded() { |
| 849 |
if (bold) {
|
| 850 |
writer.writeStartElement(ENQ_HIGHLIGHT_ELEMENT); |
| 851 |
boldOpenned = true;
|
| 852 |
} |
| 853 |
} |
| 854 |
|
| 855 |
private endBoldIfNeeded() {
|
| 856 |
if (boldOpenned) {
|
| 857 |
// println "CLOSE BOLD"
|
| 858 |
writer.writeEndElement(); // b
|
| 859 |
boldOpenned = false;
|
| 860 |
} |
| 861 |
} |
| 862 |
|
| 863 |
// private String formatTime(float time, boolean doshort)
|
| 864 |
// {
|
| 865 |
// String rez = " ";
|
| 866 |
// // if(time >= 3600) // >= 1h
|
| 867 |
// // {
|
| 868 |
// float h = time / 3600;
|
| 869 |
// time = time%3600;
|
| 870 |
// float min = (time%3600) / 60;
|
| 871 |
// int sec = (int)time%60;
|
| 872 |
//
|
| 873 |
// if(min < 10)
|
| 874 |
// rez = ""+(int)h+":0"+(int)min;//+":"+time%60;
|
| 875 |
// else
|
| 876 |
// rez = ""+(int)h+":"+(int)min;//+":"+time%60;
|
| 877 |
// //if (!doshort)
|
| 878 |
// if (sec > 9)
|
| 879 |
// rez += ":"+(int)time%60;
|
| 880 |
// else
|
| 881 |
// rez += ":0"+(int)time%60;
|
| 882 |
// // }
|
| 883 |
// // else if(time >= 60) // >= 1min
|
| 884 |
// // {
|
| 885 |
// // int min = time/60;
|
| 886 |
// // if(min < 10)
|
| 887 |
// // rez = "00:0"+min;//+":"+time%60;
|
| 888 |
// // else
|
| 889 |
// // rez = "00:"+min;//+":"+time%60;
|
| 890 |
// // if(!doshort)
|
| 891 |
// // rez += ":"+(int)time%60;
|
| 892 |
// // }
|
| 893 |
// // else // < 60
|
| 894 |
// // {
|
| 895 |
// // if(time < 10)
|
| 896 |
// // return " 0:0"+time;
|
| 897 |
// // else
|
| 898 |
// // return " 0:"+time;
|
| 899 |
// // }
|
| 900 |
// return rez;
|
| 901 |
// }
|
| 902 |
|
| 903 |
/**
|
| 904 |
* Gets the page files.
|
| 905 |
*
|
| 906 |
* @return the page files
|
| 907 |
*/
|
| 908 |
public ArrayList<File> getPageFiles() { |
| 909 |
return pages;
|
| 910 |
} |
| 911 |
|
| 912 |
/**
|
| 913 |
* Gets the idx.
|
| 914 |
*
|
| 915 |
* @return the idx
|
| 916 |
*/
|
| 917 |
public ArrayList<String> getIdx() { |
| 918 |
return indexes;
|
| 919 |
} |
| 920 |
} |