Révision 3351

TXM/trunk/org.txm.analec.rcp/src/org/txm/macro/urs/prototypes/cqp/URSUnits2CQPWordsMacro.groovy (revision 3351)
19 19 
}
20 20 

  		





  21
  21
  
    
@Field @Option(name="unit_type", usage="Corpus name in uppercase", widget="String", required=true, def="Entity")


  		





  22
  
  
    
String unit_type


  		





  
  22
  
    
		String unit_type


  		





  23
  23
  
    

  		





  24
  
  
    
@Field @Option(name="unit_properties", usage="Corpus name in uppercase", widget="String", required=true, def="Property")


  		





  25
  
  
    
String unit_properties


  		





  
  24
  
    
@Field @Option(name="unit_properties", usage=" * or comma separated list of properties names", widget="String", required=true, def="Property")


  		





  
  25
  
    
		String unit_properties


  		





  
  26
  
    
		


  		





  
  27
  
    
@Field @Option(name="unit_internal_properties", usage="Corpus name in uppercase", widget="Boolean", required=true, def="false")


  		





  
  28
  
    
def unit_internal_properties


  		





  26
  29
  
    

  		





  27
  
  
    
@Field @Option(name="unit_word", usage="Corpus name in uppercase", widget="StringArray", metaVar="START	END", required=true, def="START")


  		





  28
  
  
    
String unit_word


  		





  
  30
  
    
@Field @Option(name="unit_word", usage="CQP word position to annotate", widget="StringArray", metaVar="START	END", required=true, def="START")


  		





  
  31
  
    
		String unit_word


  		





  29
  32
  
    

  		





  30
  33
  
    
if (!ParametersDialog.open(this)) return


  		





  31
  34
  
    

  		





  32
  
  
    
MainCorpus corpus = corpusViewSelection


  		





  
  35
  
    
def corpus = corpusViewSelection


  		





  33
  36
  
    
def analecCorpus = URSCorpora.getCorpus(corpus)


  		





  34
  37
  
    

  		





  35
  38
  
    
def texts = corpus.getCorpusTextIdsList();


  		





  ......




  39
  42
  
    
for (int i = 0 ; i < texts.size() ; i++) {


  		





  40
  43
  
    
	


  		





  41
  44
  
    
	println "Processing annotations of "+texts[i]+"..."


  		





  42
  
  
    

  		





  
  45
  
    
	


  		





  43
  46
  
    
	def text_id = texts[i]


  		





  44
  47
  
    
	def text_start = texts_startlimits[i]


  		





  45
  48
  
    
	def text_end = texts_endlimits[i]


  		





  46
  
  
    

  		





  
  49
  
    
	


  		





  47
  50
  
    
	File xmltxmFile = new File(corpus.getProject().getProjectDirectory(), "txm/"+corpus.getID()+"/"+text_id+".xml")


  		





  48
  51
  
    
	File xmltxmFileCopy = new File(corpus.getProject().getProjectDirectory(), text_id+"_copy.xml")


  		





  49
  
  
    

  		





  
  52
  
    
	


  		





  50
  53
  
    
	if (!xmltxmFile.exists()) {


  		





  51
  54
  
    
		println "Warning: no text file found: "+xmltxmFile


  		





  52
  55
  
    
		continue


  		





  53
  56
  
    
	}


  		





  54
  57
  
    
	


  		





  55
  
  
    
	for (String uType : analecCorpus.getStructure().getTypes(Unite.class)) {


  		





  56
  
  
    
		def corpus_units = []


  		





  57
  
  
    
		ArrayList<Unite> all_units = analecCorpus.getUnites(uType)


  		





  58
  
  
    
		corpus_units = all_units.findAll() {


  		





  59
  
  
    
			unit_type.equals(it.getProp("type")) && text_start <= it.getDeb() && it.getFin() < text_end


  		





  60
  
  
    
		}


  		





  61
  
  
    
		


  		





  62
  
  
    
		if (corpus_units.size() == 0) continue;


  		





  63
  
  
    
		


  		





  64
  
  
    
		try {


  		





  65
  
  
    
			println " processing word Units ${text_id} and its '$uType' units ("+corpus_units.size()+")"


  		





  66
  
  
    
			WordUnitsInserter inserter = new WordUnitsInserter(corpus, xmltxmFile, corpus_units, unit_properties, unit_word);


  		





  67
  
  
    
			if (inserter.process(xmltxmFileCopy) && ValidateXml.test(xmltxmFileCopy)) {


  		





  68
  
  
    
				xmltxmFile.delete()


  		





  69
  
  
    
				xmltxmFileCopy.renameTo(xmltxmFile)


  		





  70
  
  
    

  		





  71
  
  
    
				println "Done, "+corpus_units.size()+ " units written"


  		





  72
  
  
    

  		





  73
  
  
    
			} else {


  		





  74
  
  
    
				println "Error while processing the XML-TXM $xmltxmFile file"


  		





  75
  
  
    
				File error = new File(corpus.getProject().getProjectDirectory(), "error/"+xmltxmFile.getName())


  		





  76
  
  
    
				error.getParentFile().mkdirs()


  		





  77
  
  
    
				println "	moving created file to $error"


  		





  78
  
  
    
				error.delete()


  		





  79
  
  
    
				xmltxmFileCopy.renameTo(error)


  		





  80
  
  
    
			}


  		





  81
  
  
    
		} catch(Exception e) {


  		





  82
  
  
    
			println "Error while processing milestones $xmltxmFile file: "+e


  		





  83
  
  
    
			e.printStackTrace();


  		





  
  58
  
    
	def corpus_units = []


  		





  
  59
  
    
	ArrayList<Unite> all_units = analecCorpus.getUnites(unit_type)


  		





  
  60
  
    
	corpus_units = all_units.findAll() {


  		





  
  61
  
    
		text_start <= it.getDeb() && it.getFin() < text_end


  		





  
  62
  
    
	}


  		





  
  63
  
    
	


  		





  
  64
  
    
	if (corpus_units.size() == 0) {


  		





  
  65
  
    
		println " No '$unit_type' unit found."


  		





  
  66
  
    
		continue;


  		





  
  67
  
    
	}


  		





  
  68
  
    
	


  		





  
  69
  
    
	try {


  		





  
  70
  
    
		println " Processing word Units ${text_id} and its '$unit_type' units ("+corpus_units.size()+")"


  		





  
  71
  
    
		WordUnitsInserter inserter = new WordUnitsInserter(corpus, xmltxmFile, corpus_units, unit_properties, unit_word, unit_internal_properties);


  		





  
  72
  
    
		if (inserter.process(xmltxmFileCopy) && ValidateXml.test(xmltxmFileCopy)) {


  		





  
  73
  
    
			xmltxmFile.delete()


  		





  
  74
  
    
			xmltxmFileCopy.renameTo(xmltxmFile)


  		





  
  75
  
    
			


  		





  
  76
  
    
			println "Done, "+corpus_units.size()+ " units written"


  		





  
  77
  
    
			


  		





  
  78
  
    
		} else {


  		





  
  79
  
    
			println "Error while processing the XML-TXM $xmltxmFile file"


  		





  84
  80
  
    
			File error = new File(corpus.getProject().getProjectDirectory(), "error/"+xmltxmFile.getName())


  		





  85
  81
  
    
			error.getParentFile().mkdirs()


  		





  86
  82
  
    
			println "	moving created file to $error"


  		





  87
  83
  
    
			error.delete()


  		





  88
  84
  
    
			xmltxmFileCopy.renameTo(error)


  		





  89
  85
  
    
		}


  		





  
  86
  
    
	} catch(Exception e) {


  		





  
  87
  
    
		println "Error while processing milestones $xmltxmFile file: "+e


  		





  
  88
  
    
		e.printStackTrace();


  		





  
  89
  
    
		File error = new File(corpus.getProject().getProjectDirectory(), "error/"+xmltxmFile.getName())


  		





  
  90
  
    
		error.getParentFile().mkdirs()


  		





  
  91
  
    
		println "	moving created file to $error"


  		





  
  92
  
    
		error.delete()


  		





  
  93
  
    
		xmltxmFileCopy.renameTo(error)


  		





  90
  94
  
    
	}


  		





  91
  95
  
    
}


  		












  

    
      TXM/trunk/org.txm.analec.rcp/src/org/txm/macro/urs/prototypes/cqp/WordUnitsInserter.groovy	(revision 3351)
    
  






  21
  21
  
    
	File inputFile


  		





  22
  22
  
    
	def id2Units = [:]


  		





  23
  23
  
    
	def unit_properties // "*" or list (String)


  		





  
  24
  
    
	def unit_internal_properties = false


  		





  24
  25
  
    
	def unit_word // ALL START END


  		





  25
  26
  
    
	LinkedHashMap<String, String> anaValues = new LinkedHashMap<String, String>();


  		





  26
  27
  
    

  		





  27
  
  
    
	public WordUnitsInserter(MainCorpus corpus, File inputFile, List<Unite> units, String unit_properties, String unit_word) {


  		





  
  28
  
    
	public WordUnitsInserter(MainCorpus corpus, File inputFile, List<Unite> units, String unit_properties, String unit_word, boolean unit_internal_properties) {


  		





  28
  29
  
    
		super(inputFile)


  		





  29
  30
  
    
		this.inputFile = inputFile


  		





  30
  31
  
    
		


  		





  
  32
  
    
		this.unit_internal_properties = unit_internal_properties


  		





  31
  33
  
    
		this.unit_properties = unit_properties


  		





  32
  34
  
    
		this.unit_word = unit_word


  		





  33
  35
  
    
		if (!("*".equals(unit_properties))) {


  		





  ......




  84
  86
  
    
						


  		





  85
  87
  
    
						if (!anaValues.containsKey(p)) {


  		





  86
  88
  
    
							anaValues[p] = ""


  		





  87
  
  
    
							ana_resp = "#txm"


  		





  
  89
  
    
							ana_resp = "#urs"


  		





  88
  90
  
    
						}


  		





  89
  91
  
    
						anaValues[p] = (anaValues[p]+" "+props.get(p)).trim()


  		





  90
  92
  
    
					}


  		





  
  93
  
    
					if (unit_internal_properties) {


  		





  
  94
  
    
	


  		





  
  95
  
    
						anaValues["urs-type"] = u.getType()


  		





  
  96
  
    
						anaValues["urs-start"] = ""+u.getDeb()


  		





  
  97
  
    
						anaValues["urs-end"] = ""+u.getFin()


  		





  
  98
  
    
					}


  		





  91
  99
  
    
				}


  		





  92
  100
  
    
				if (anaValues.size() > 0) println anaValues


  		





  93
  101
  
    
			}


  		












Formats disponibles :
  Unified diff