Révision 3624
| TXM/trunk/org.txm.groovy.core/src/groovy/org/txm/macro/export/ExportTextsContentMacro.groovy (revision 3624) | ||
|---|---|---|
| 16 | 16 |
import org.txm.rcp.swt.widget.parameters.* |
| 17 | 17 |
|
| 18 | 18 |
if (!(corpusViewSelection instanceof CQPCorpus)) {
|
| 19 |
println "Please select a corpus"
|
|
| 20 |
return |
|
| 21 |
} |
|
| 19 |
monitorShowError("Erreur : la sélection dans la vue Corpus n'est pas un corpus ou un sous-corpus ($corpusViewSelection).")
|
|
| 20 |
return false
|
|
| 21 |
}
|
|
| 22 | 22 |
|
| 23 | 23 |
// PARAMETERS |
| 24 | 24 |
|
| ... | ... | |
| 31 | 31 |
@Field @Option(name="oneWordPerLine", usage="output one word per line", widget="Boolean", required=false, def="false") |
| 32 | 32 |
def oneWordPerLine |
| 33 | 33 |
|
| 34 |
@Field @Option(name="oneSentencePerLine", usage="output one sentence per line", widget="Boolean", required=false, def="true")
|
|
| 34 |
@Field @Option(name="oneSentencePerLine", usage="output one sentence per line", widget="Boolean", required=false, def="false")
|
|
| 35 | 35 |
def oneSentencePerLine |
| 36 | 36 |
|
| 37 | 37 |
@Field @Option(name="sentenceStructureName", usage="name of the structure encoding sentences", widget="String", required=false, def="") |
| ... | ... | |
| 44 | 44 |
if (!outputDirectory.exists()) outputDirectory.mkdirs() |
| 45 | 45 |
|
| 46 | 46 |
def corpus = corpusViewSelection |
| 47 |
corpus.compute() |
|
| 48 |
def mainCorpus = corpus.getMainCorpus() |
|
| 47 | 49 |
def corpusName = corpus.getName() |
| 48 | 50 |
def CQI = CQPSearchEngine.getCqiClient() |
| 49 | 51 |
|
| ... | ... | |
| 78 | 80 |
return 1 |
| 79 | 81 |
} |
| 80 | 82 |
|
| 81 |
def textidProperty = corpus.getStructuralUnit("text").getProperty("id")
|
|
| 82 |
def textStartBoundaries = corpus.getTextStartLimits() |
|
| 83 |
def textEndBoundaries = corpus.getTextEndLimits() |
|
| 83 |
def textidProperty = mainCorpus.getStructuralUnit("text").getProperty("id")
|
|
| 84 |
def textStartBoundaries = mainCorpus.getTextStartLimits() |
|
| 85 |
def textEndBoundaries = mainCorpus.getTextEndLimits() |
|
| 86 |
|
|
| 84 | 87 |
int[] struct_pos = CQI.cpos2Struc(textidProperty.getQualifiedName(), textStartBoundaries) |
| 85 |
String[] textids = CQI.struc2Str(textidProperty.getQualifiedName(), struct_pos)
|
|
| 88 |
String[] allTextIds = CQI.struc2Str(textidProperty.getQualifiedName(), struct_pos)
|
|
| 86 | 89 |
|
| 87 |
if (textStartBoundaries.size() == 1) {
|
|
| 88 |
println "1 text" |
|
| 90 |
corpusTextIds = new HashSet<String>(corpus.getStructuralUnit("text").getProperty("id").getValues(corpus))
|
|
| 91 |
|
|
| 92 |
// https://stackoverflow.com/questions/150750/hashset-vs-list-performance |
|
| 93 |
|
|
| 94 |
if (corpusTextIds.size() == 1) {
|
|
| 95 |
println "1 text ("+corpusTextIds+")"
|
|
| 89 | 96 |
} else {
|
| 90 |
println ""+textStartBoundaries.size()+" texts"
|
|
| 97 |
println ""+corpusTextIds.size()+" texts ("+corpusTextIds+")"
|
|
| 91 | 98 |
} |
| 92 | 99 |
|
| 93 |
for (int i = 0 ; i < textStartBoundaries.size() ; i++) {
|
|
| 94 |
int start = textStartBoundaries[i] |
|
| 95 |
int end = textEndBoundaries[i] |
|
| 100 |
for (int i = 0; i < textStartBoundaries.size(); i++) {
|
|
| 96 | 101 |
|
| 97 |
File txtFile = new File(outputDirectory, textids[i]+".txt") |
|
| 98 |
print "." |
|
| 99 |
def writer = txtFile.newWriter("UTF-8")
|
|
| 100 |
int[] positions = new int[end - start + 1] |
|
| 101 |
int c = 0 |
|
| 102 |
for (int p : start..end) {
|
|
| 103 |
positions[c++] = p |
|
| 104 |
} |
|
| 105 |
int[] idx = CQI.cpos2Id(wordPropertyI.getQualifiedName(), positions) |
|
| 106 |
def words = CQI.id2Str(wordPropertyI.getQualifiedName(), idx) |
|
| 107 |
def tmp = [] |
|
| 108 |
for (int j = 0 ; j < positions.length ; j++) {
|
|
| 109 |
int p = positions[j] |
|
| 110 |
tmp << words[j] |
|
| 111 |
if (oneSentencePerLine && breaks_pos.contains(p)) {
|
|
| 112 |
if (oneWordPerLine) {
|
|
| 113 |
tmp.each { word -> writer.println word }
|
|
| 114 |
} else {
|
|
| 115 |
writer.println LangFormater.format(tmp.join(" "), corpus.getLang())
|
|
| 116 |
} |
|
| 117 |
tmp = [] |
|
| 118 |
} |
|
| 119 |
} |
|
| 120 |
if (tmp.size() > 0) {
|
|
| 121 |
if (oneWordPerLine) {
|
|
| 122 |
tmp.each { word -> writer.println word }
|
|
| 123 |
} else {
|
|
| 124 |
writer.println LangFormater.format(tmp.join(" "), corpus.getLang())
|
|
| 125 |
} |
|
| 126 |
} |
|
| 127 |
writer.close() |
|
| 102 |
if (corpusTextIds.contains(allTextIds[i])) {
|
|
| 103 |
|
|
| 104 |
int start = textStartBoundaries[i] |
|
| 105 |
int end = textEndBoundaries[i] |
|
| 106 |
File txtFile = new File(outputDirectory, allTextIds[i] + ".txt") |
|
| 107 |
|
|
| 108 |
def writer = txtFile.newWriter("UTF-8")
|
|
| 109 |
int [] positions = new int [end - start + 1] |
|
| 110 |
int c = 0 |
|
| 111 |
for (int p: start..end) {
|
|
| 112 |
positions[c++] = p |
|
| 113 |
} |
|
| 114 |
int [] idx = CQI.cpos2Id(wordPropertyI.getQualifiedName(), positions) |
|
| 115 |
def words = CQI.id2Str(wordPropertyI.getQualifiedName(), idx) |
|
| 116 |
def tmp = [] |
|
| 117 |
for (int j = 0; j < positions.length; j++) {
|
|
| 118 |
int p = positions[j] |
|
| 119 |
tmp << words[j] |
|
| 120 |
if (oneSentencePerLine && breaks_pos.contains(p)) {
|
|
| 121 |
if (oneWordPerLine) {
|
|
| 122 |
tmp.each {
|
|
| 123 |
word -> writer.println word |
|
| 124 |
} |
|
| 125 |
} else {
|
|
| 126 |
writer.println LangFormater.format(tmp.join(" "), corpus.getLang())
|
|
| 127 |
} |
|
| 128 |
tmp = [] |
|
| 129 |
} |
|
| 130 |
} |
|
| 131 |
if (tmp.size() > 0) {
|
|
| 132 |
if (oneWordPerLine) {
|
|
| 133 |
tmp.each {
|
|
| 134 |
word -> writer.println word |
|
| 135 |
} |
|
| 136 |
} else {
|
|
| 137 |
writer.println LangFormater.format(tmp.join(" "), corpus.getLang())
|
|
| 138 |
} |
|
| 139 |
} |
|
| 140 |
writer.close() |
|
| 141 |
} |
|
| 128 | 142 |
} |
| 129 | 143 |
|
| 130 |
println "\nDone, result saved in "+outputDirectory.getAbsolutePath() |
|
| 144 |
println "Done, result saved in "+outputDirectory.getAbsolutePath() |
|
| 145 |
|
|
| 146 |
def monitorShowError(String message) {
|
|
| 147 |
monitor.syncExec(new Runnable() {
|
|
| 148 |
public void run() {
|
|
| 149 |
org.eclipse.jface.dialogs.MessageDialog.openError(org.eclipse.swt.widgets.Display.getCurrent().getActiveShell(), "Erreur", message) |
|
| 150 |
} |
|
| 151 |
}) |
|
| 152 |
} |
|
Formats disponibles : Unified diff