Révision 3485

TXM/trunk/org.txm.groovy.core/src/groovy/org/txm/scripts/importer/transcriber/compiler.groovy (revision 3485)
585 585 
							break;
586 586 
						case "w":
587 587 
						// concat spk id and ref
588 
							String isEnq = (interviewers != null && interviewers.matches(u_name))?"*":"";
588 
							String isEnq = (interviewers != null && interviewers.contains(u_name))?"*":"";
589 589 
							String ref = (u_name+", "+formatedTime+""+isEnq)
590 590 
							if (ADD_TEXTID_TO_REF) ref = textid+", "+ref
591 591 
							vForm +="\t"+u_name+"\t"+ref
......
615 615 
							vForm = vForm.replaceAll("\n", "").replaceAll("&", "&amp;").replaceAll("<", "&lt;");
616 616
617 617 
							if (interviewers != null && !indexInterviewer) { // we must remove some words
618 
								if (!interviewers.matches(u_name)) { // keep what is now an interviewer
618 
								if (!interviewers.contains(u_name)) { // keep what is now an interviewer
619 619 
									output.write(vForm+"\t"+wordid+vAna+"\n");
620 620 
								}
621 621 
							} else {
TXM/trunk/org.txm.groovy.core/src/groovy/org/txm/scripts/importer/transcriber/pager.groovy (revision 3485)
922 922
923 923 
		writer.writeStartElement("span");
924 924 
		writer.writeAttribute("class", "spk");
925 
		bold = interviewers != null && interviewers.matches(spk)
925 
		bold = interviewers != null && interviewers.contains(spk)
926 926 
		spk = spk.replaceAll('^([^0-9]*)([0-9]+)$', '$1 $2');
927 927 
		if (overlapping) {
928 928 
			writer.writeCharacters("// ")
TXM/trunk/org.txm.groovy.core/src/groovy/org/txm/macro/txt/SearchInDirectoryMacro.groovy (revision 3485)
21 21 
String regexp;
22 22 
@Field @Option(name="encoding", usage="File encoding", widget="String", required=false, def="UTF-8")
23 23 
String encoding;
24 
@Field @Option(name="showLines", usage="File encoding", widget="Boolean", required=false, def="true")
25 
Boolean showLines;
24 26 

  		





  25
  27
  
    
if (!ParametersDialog.open(this)) return;


  		





  26
  28
  
    

  		





  ......




  38
  40
  
    
		}


  		





  39
  41
  
    
	}


  		





  40
  42
  
    
	


  		





  41
  
  
    
	println inputfile.getName() + " "+lines.size() + " match" +((lines.size() > 1)?"s":"")


  		





  42
  43
  
    
	if (lines.size() > 0) {


  		





  43
  
  
    
		for (String s : lines ) println s


  		





  
  44
  
    
		println inputfile.getName() + " "+lines.size() + " match" +((lines.size() > 1)?"s":"")


  		





  
  45
  
    
		if (showLines && lines.size() > 0) {


  		





  
  46
  
    
			for (String s : lines ) println s


  		





  
  47
  
    
		}


  		





  44
  48
  
    
	}


  		





  
  49
  
    
	


  		





  45
  50
  
    
}


  		












  

    
      TXM/trunk/org.txm.groovy.core/src/groovy/org/txm/macro/projects/nov13/PrepareTranscriptionsMacro.groovy	(revision 3485)
    
  






  11
  11
  
    

  		





  12
  12
  
    
@Field @Option(name="resultDirectory", usage="The result directory", widget="Folder", required=false, def="")


  		





  13
  13
  
    
		File resultDirectory


  		





  14
  
  
    
		


  		





  
  14
  
    

  		





  15
  15
  
    
@Field @Option(name="primarySpeakerIdRegex", usage="speaker ID of the primary speaker", widget="String", required=false, def="")


  		





  16
  16
  
    
		String primarySpeakerIdRegex


  		





  17
  17
  
    

  		





  18
  18
  
    
@Field @Option(name="otherNonPrimarySpeakerId", usage="other non primary id of the other turns", widget="String", required=false, def="")


  		





  19
  19
  
    
		String otherNonPrimarySpeakerId


  		





  20
  
  
    
		


  		





  
  20
  
    

  		





  21
  21
  
    
@Field @Option(name="nonPrimarySpeakerIdRegex", usage="other non primary id of the other turns", widget="String", required=false, def="")


  		





  22
  22
  
    
		String nonPrimarySpeakerIdRegex


  		





  23
  
  
    
		


  		





  24
  
  
    
@Field @Option(name="supplementarySpeakerIdRegex", usage="supplementary locutor ids regex", widget="String", required=false, def="UX.+")


  		





  25
  
  
    
		String supplementarySpeakerIdRegex


  		





  26
  
  
    
		


  		





  27
  
  
    
@Field @Option(name="supplementarySpeakerId", usage="supplementary locutor id to normalize", widget="String", required=false, def="")


  		





  28
  
  
    
		String supplementarySpeakerId


  		





  29
  
  
    
		


  		





  
  23
  
    

  		





  
  24
  
    
//@Field @Option(name="supplementarySpeakerIdRegex", usage="supplementary locutor ids regex", widget="String", required=false, def="UX.+")


  		





  
  25
  
    
//		String supplementarySpeakerIdRegex


  		





  
  26
  
    
//


  		





  
  27
  
    
//@Field @Option(name="supplementarySpeakerId", usage="supplementary locutor id to normalize", widget="String", required=false, def="")


  		





  
  28
  
    
//		String supplementarySpeakerId


  		





  
  29
  
    

  		





  
  30
  
    
@Field @Option(name="spearkerReplacementTableFile", usage="2 columns (from, to) table file", widget="File", required=false, def="replacements.tsv")


  		





  
  31
  
    
		File spearkerReplacementTableFile


  		





  
  32
  
    

  		





  30
  33
  
    
@Field @Option(name="newSectionMarker", usage="section marker", widget="String", required=false, def="*#")


  		





  31
  34
  
    
		String newSectionMarker


  		





  32
  35
  
    

  		





  33
  36
  
    
@Field @Option(name="debug", usage="speaker ID of the primary speaker", widget="Boolean", required=false, def="false")


  		





  34
  37
  
    
		Boolean debug


  		





  35
  
  
    
		


  		





  
  38
  
    

  		





  36
  39
  
    
@Field @Option(name="cleanWorkingDirectories", usage="Clean working directories is selected", widget="Boolean", required=false, def="true")


  		





  37
  40
  
    
		Boolean cleanWorkingDirectories


  		





  38
  
  
    
		


  		





  
  41
  
    

  		





  39
  42
  
    
if (!ParametersDialog.open(this)) return;


  		





  40
  43
  
    

  		





  41
  44
  
    
if (resultDirectory.equals(vocapiaDirectory)) {


  		





  ......




  124
  127
  
    
	return false


  		





  125
  128
  
    
}


  		





  126
  129
  
    

  		





  
  130
  
    
def replacements = []


  		





  
  131
  
    
if (spearkerReplacementTableFile.exists()) {


  		





  
  132
  
    
	for (String line : spearkerReplacementTableFile.readLines("UTF-8")) {


  		





  
  133
  
    
		def split = line.split("\t", 2)


  		





  
  134
  
    
		if (split.length == 2) {


  		





  
  135
  
    
			replacements << [split[0].replaceAll("<SPACE>", " ").replaceAll("<BOM>", "\uFEFF"), split[1]]


  		





  
  136
  
    
		}


  		





  
  137
  
    
	}


  		





  
  138
  
    
}


  		





  
  139
  
    

  		





  127
  140
  
    
cpb = new ConsoleProgressBar(trsFiles.size())


  		





  128
  141
  
    
for (File file : trsFiles) {


  		





  129
  142
  
    
	if (debug) println "== $file =="


  		





  ......




  140
  153
  
    
		if (debug) {println "DEBUG ACTIVATED -> STOP"; return;}


  		





  141
  154
  
    
	}


  		





  142
  155
  
    
	


  		





  
  156
  
    
	


  		





  
  157
  
    
	File tmpFile2 = new File(resultDirectory, "tmp2.xml")


  		





  
  158
  
    
	for (def replacement : replacements) {


  		





  
  159
  
    
		


  		





  
  160
  
    
		RecodeSpeakers fixer2 = new RecodeSpeakers(tmpFile, tmpFile2, replacement[0], null, replacement[1], replacement[1])


  		





  
  161
  
    
		fixer2.debug = debug


  		





  
  162
  
    
		


  		





  
  163
  
    
		if (!fixer2.process()) {


  		





  
  164
  
    
			println "WARNING: ERROR WHILE PROCESSING: "+file


  		





  
  165
  
    
			if (debug) {println "DEBUG ACTIVATED -> STOP"; return;}


  		





  
  166
  
    
		}


  		





  
  167
  
    
		tmpFile.delete(); // This tmp file must be removed for the next operation


  		





  
  168
  
    
		tmpFile2.renameTo(tmpFile)


  		





  
  169
  
    
	}


  		





  
  170
  
    
	


  		





  143
  171
  
    
	File outFile2 = new File(resultDirectory, file.getName())


  		





  144
  
  
    
	RecodeSpeakers fixer2 = new RecodeSpeakers(tmpFile, outFile2, supplementarySpeakerIdRegex, null, supplementarySpeakerId, supplementarySpeakerId)


  		





  145
  
  
    
	fixer2.debug = debug


  		





  
  172
  
    
	tmpFile.renameTo(outFile2)


  		





  146
  173
  
    
	


  		





  147
  
  
    
	if (!fixer2.process()) {


  		





  148
  
  
    
		println "WARNING: ERROR WHILE PROCESSING: "+file


  		





  149
  
  
    
		if (debug) {println "DEBUG ACTIVATED -> STOP"; return;}


  		





  150
  
  
    
	}


  		





  151
  
  
    
	tmpFile.delete(); // This tmp file must be removed for the next operation


  		





  152
  174
  
    
}


  		





  153
  175
  
    
cpb.done()


  		





  154
  176
  
    

  		












  

    
      TXM/trunk/org.txm.groovy.core/src/groovy/org/txm/macro/transcription/Vocapia2Transcriber.groovy	(revision 3485)
    
  






  81
  81
  
    
								break;


  		





  82
  82
  
    
							case "Speaker": // <Speaker ch="1" dur="531.38" gender="X" spkid="Enquêtrice" lang="fre" lconf="1.00" nw="1586" tconf="0.95"/> -> <Speaker id="spk1" name="enq4" check="no" dialect="native" accent="" scope="local"/>


  		





  83
  83
  
    
							


  		





  84
  
  
    
								String spkid = parser.getAttributeValue(null, "spkid").trim().replaceAll("[\\s()]", "")


  		





  
  84
  
    
								String spkid = parser.getAttributeValue(null, "spkid").trim().replaceAll("[\\s\\uFEFF]", "")


  		





  85
  85
  
    
								


  		





  86
  86
  
    
								writer.writeStartElement("Speaker")


  		





  87
  87
  
    
								writer.writeAttribute("id", spkid)


  		












Formats disponibles :
  Unified diff