Révision 2246
| tmp/org.txm.groovy.core/src/java/org/txm/groovy/core/GroovyProgressMonitor.java (revision 2246) | ||
|---|---|---|
| 60 | 60 |
|
| 61 | 61 |
@Override |
| 62 | 62 |
public void subTask(String name) {
|
| 63 |
// TODO Auto-generated method stub
|
|
| 63 |
if (monitor == null) return;
|
|
| 64 | 64 |
|
| 65 |
monitor.subTask(name); |
|
| 65 | 66 |
} |
| 66 | 67 |
|
| 67 | 68 |
@Override |
| tmp/org.txm.groovy.core/src/java/org/txm/groovy/core/GroovyScriptedImportEngine.java (revision 2246) | ||
|---|---|---|
| 69 | 69 |
// CorpusBuild c = project.getCorpora().get(0); |
| 70 | 70 |
// c.delete(); |
| 71 | 71 |
// } |
| 72 |
List<Text> texts = project.getTexts(); |
|
| 73 |
for (Text t : texts) {
|
|
| 74 |
while (t.getEditions().size() > 0) {
|
|
| 75 |
Edition ed = t.getEditions().get(0); |
|
| 76 |
ed.delete(); |
|
| 77 |
} |
|
| 78 |
} |
|
| 72 |
// List<Text> texts = project.getTexts();
|
|
| 73 |
// for (Text t : texts) {
|
|
| 74 |
// while (t.getEditions().size() > 0) {
|
|
| 75 |
// Edition ed = t.getEditions().get(0);
|
|
| 76 |
// ed.delete();
|
|
| 77 |
// }
|
|
| 78 |
// }
|
|
| 79 | 79 |
} else {
|
| 80 | 80 |
// clear all children |
| 81 | 81 |
while (project.getChildren().size() > 0) {
|
| ... | ... | |
| 93 | 93 |
// if (errorBinDirectory.exists()) DeleteDir.deleteDirectory(errorBinDirectory); |
| 94 | 94 |
|
| 95 | 95 |
//this.setCurrentMonitor(monitor); |
| 96 |
monitor.beginTask("Importing sources" + project.getSrcdir(), 100); //$NON-NLS-1$
|
|
| 96 |
monitor.beginTask("Importing sources " + project.getSrcdir(), 100); //$NON-NLS-1$
|
|
| 97 | 97 |
|
| 98 | 98 |
//org.txm.Toolbox.shutdownSearchEngine(); |
| 99 | 99 |
monitor.worked(5); |
| tmp/org.txm.groovy.core/src/groovy/org/txm/macro/prototypes/stats/AFCMacro.groovy (revision 2246) | ||
|---|---|---|
| 1 |
// STANDARD DECLARATIONS |
|
| 2 |
package org.txm.macro |
|
| 3 |
|
|
| 4 |
import org.kohsuke.args4j.* |
|
| 5 |
import groovy.transform.Field |
|
| 6 |
import org.txm.rcpapplication.swt.widget.parameters.* |
|
| 7 |
import org.txm.searchengine.cqp.clientExceptions.* |
|
| 8 |
import org.txm.searchengine.cqp.corpus.* |
|
| 9 |
import org.txm.searchengine.cqp.corpus.query.* |
|
| 10 |
import org.apache.commons.lang.time.StopWatch |
|
| 11 |
import java.util.Arrays |
|
| 12 |
import org.jfree.chart.renderer.xy.* |
|
| 13 |
import org.jfree.chart.renderer.* |
|
| 14 |
import org.jfree.chart.plot.* |
|
| 15 |
import org.jfree.data.xy.* |
|
| 16 |
import org.jfree.chart.axis.* |
|
| 17 |
import java.awt.*; |
|
| 18 |
import java.awt.geom.*; |
|
| 19 |
import org.jfree.chart.labels.* |
|
| 20 |
|
|
| 21 |
import org.txm.ca.core.chartsengine.jfreechart.themes.highcharts.renderers.* |
|
| 22 |
import org.txm.ca.rcp.editors.* |
|
| 23 |
import org.txm.libs.office.ReadODS |
|
| 24 |
import org.txm.ca.core.chartsengine.jfreechart.datasets.* |
|
| 25 |
import org.jfree.chart.renderer.AbstractRenderer |
|
| 26 |
|
|
| 27 |
println "editor: "+editor |
|
| 28 |
|
|
| 29 |
if (!(editor instanceof CAEditor)) {
|
|
| 30 |
println "editor is not a CA editor: $editor, Run the macro with F12 when the editor is selected :-)" |
|
| 31 |
return |
|
| 32 |
} |
|
| 33 |
|
|
| 34 |
@Field @Option(name="patternsODSFile", usage="The starting word", widget="FileOpen", required=true, def='patterns.ods') |
|
| 35 |
def patternsODSFile |
|
| 36 |
@Field @Option(name="debug", usage="Show internal variable content", widget="StringArray", metaVar="OFF ON ALL REALLY ALL", required=true, def="OFF") |
|
| 37 |
debug |
|
| 38 |
|
|
| 39 |
// Open the parameters input dialog box |
|
| 40 |
if (!ParametersDialog.open(this)) return; |
|
| 41 |
if (debug == "OFF") debug = 0; else if (debug == "ON") debug = 1; else if (debug == "ALL") debug = 2 else if (debug == "REALLY ALL") debug = 3 |
|
| 42 |
|
|
| 43 |
if (!patternsODSFile.exists()) {
|
|
| 44 |
println "Pattern file not found: $patternsODSFile" |
|
| 45 |
return false; |
|
| 46 |
} |
|
| 47 |
if (!patternsODSFile.isFile() || !patternsODSFile.getName().toLowerCase().endsWith(".ods")) {
|
|
| 48 |
println "Wrong pattern file: $patternsODSFile" |
|
| 49 |
return false; |
|
| 50 |
} |
|
| 51 |
|
|
| 52 |
def data = ReadODS.toTable(patternsODSFile, "rows") |
|
| 53 |
def keys = data[0] |
|
| 54 |
def row_styles = [:] // reformat data |
|
| 55 |
for (int i = 1 ; i < data.size() ; i++) {
|
|
| 56 |
def h = data[i] |
|
| 57 |
def style = [:] // create style entry |
|
| 58 |
String s = h[0]; |
|
| 59 |
row_styles[/$s/] = style // with a regexp pattern as key |
|
| 60 |
|
|
| 61 |
// fill the style |
|
| 62 |
for (int j = 1 ; j < h.size() ; j++) {
|
|
| 63 |
style[keys[j]] = h[j] |
|
| 64 |
} |
|
| 65 |
} |
|
| 66 |
if (debug > 0) {
|
|
| 67 |
println "ROW STYLES=$row_styles" |
|
| 68 |
} |
|
| 69 |
|
|
| 70 |
data = ReadODS.toTable(patternsODSFile, "cols") |
|
| 71 |
keys = data[0] |
|
| 72 |
def col_styles = [:] // reformat data |
|
| 73 |
for (int i = 1 ; i < data.size() ; i++) {
|
|
| 74 |
def h = data[i] |
|
| 75 |
def style = [:] // create style entry |
|
| 76 |
String s = h[0]; |
|
| 77 |
col_styles[/$s/] = style // with a regexp pattern as key |
|
| 78 |
|
|
| 79 |
// fill the style |
|
| 80 |
for (int j = 1 ; j < h.size() ; j++) {
|
|
| 81 |
style[keys[j]] = h[j] |
|
| 82 |
} |
|
| 83 |
} |
|
| 84 |
if (debug > 0) {
|
|
| 85 |
println "COL STYLES=$col_styles" |
|
| 86 |
} |
|
| 87 |
|
|
| 88 |
ica = editor.getCA() |
|
| 89 |
ca = ica.getCA() |
|
| 90 |
|
|
| 91 |
// http://txm.sourceforge.net/javadoc/TXM/TBX/org/txm/stat/engine/r/function/CA.html |
|
| 92 |
|
|
| 93 |
// SOME DATA |
|
| 94 |
rows = ica.getRowNames() |
|
| 95 |
rowsinfo = ica.getRowInfos() |
|
| 96 |
rowscos2 = ca.getRowCos2() |
|
| 97 |
cols = ica.getColNames() |
|
| 98 |
println cols |
|
| 99 |
colssinfo = ica.getColInfos() |
|
| 100 |
colscos2 = ca.getColCos2() |
|
| 101 |
D1 = ica.getFirstDimension() -1; |
|
| 102 |
D2 = ica.getSecondDimension() -1; |
|
| 103 |
|
|
| 104 |
shapes = [:] |
|
| 105 |
shapes["square"] = AbstractRenderer.DEFAULT_SHAPE; |
|
| 106 |
shapes["circle"] = AbstractRenderer.DEFAULT_SHAPE; |
|
| 107 |
shapes["triangle"] = AbstractRenderer.DEFAULT_SHAPE; |
|
| 108 |
shapes["star"] = AbstractRenderer.DEFAULT_SHAPE; |
|
| 109 |
shapes["disk"] = AbstractRenderer.DEFAULT_SHAPE; |
|
| 110 |
|
|
| 111 |
// styles per col index in dataset |
|
| 112 |
// set col points label |
|
| 113 |
colLabelStyle = new HashMap<Integer, String>(); |
|
| 114 |
// set col points visibility |
|
| 115 |
colHiddenStyle = new HashSet<Integer>(); // true false |
|
| 116 |
// set col font size |
|
| 117 |
colFontSizeStyle = new HashMap<Integer, Integer>(); // 0.0 to 10.0 |
|
| 118 |
// set col points size |
|
| 119 |
colSizeStyle = new HashMap<Integer, Double>(); // 0.0 to 10.0 |
|
| 120 |
// set col points RGBA color |
|
| 121 |
colColorStyle = new HashMap<Integer, Color>(); |
|
| 122 |
// set col points shape (circle, square, triangle, ... + color ? + size ?) -> expert |
|
| 123 |
colShapeStyle = new HashMap<Integer, Shape>(); // circle, square, triangle, etc. |
|
| 124 |
|
|
| 125 |
|
|
| 126 |
rowLabelStyle = new HashMap<Integer, String>(); |
|
| 127 |
// set row points visibility |
|
| 128 |
rowHiddenStyle = new HashSet<Integer>(); // true false |
|
| 129 |
// set row font size |
|
| 130 |
rowFontSizeStyle = new HashMap<Integer, Integer>(); // 0.0 to 10.0 |
|
| 131 |
// set row points size |
|
| 132 |
rowSizeStyle = new HashMap<Integer, Double>(); // 0.0 to 10.0 |
|
| 133 |
// set row points RGBA color |
|
| 134 |
rowColorStyle = new HashMap<Integer, Color>(); |
|
| 135 |
// set row points shape (circle, square, triangle, ... + color ? + size ?) -> expert |
|
| 136 |
rowShapeStyle = new HashMap<Integer, Shape>(); // circle, square, triangle, etc. |
|
| 137 |
|
|
| 138 |
// prepare col style data for the dataset |
|
| 139 |
for (int i = 0 ; i < cols.length ; i++) {
|
|
| 140 |
for (def p : col_styles.keySet()) {
|
|
| 141 |
if (cols[i] ==~ p) {
|
|
| 142 |
def style = col_styles[p] |
|
| 143 |
if (style["shape"] != null && shapes.containsKey(style["shape"])) {
|
|
| 144 |
colShapeStyle[i] = shapes[style["shape"]] |
|
| 145 |
} |
|
| 146 |
if (style["color"] != null && style["color"].length() > 0 ) {
|
|
| 147 |
colColorStyle[i] = new Color(Integer.parseInt(style["color"]), true) |
|
| 148 |
} |
|
| 149 |
if (style["label"] != null && style["label"].length() > 0) {
|
|
| 150 |
colLabelStyle[i] = style["label"] |
|
| 151 |
} |
|
| 152 |
if (style["size"] != null && style["size"].length() > 0) {
|
|
| 153 |
colSizeStyle[i] = Double.parseDouble(style["size"]) |
|
| 154 |
} |
|
| 155 |
if (style["font-size"] != null && style["font-size"].length() > 0) {
|
|
| 156 |
colFontSizeStyle[i] = Integer.parseInt(style["font-size"]) |
|
| 157 |
} |
|
| 158 |
if (style["hidden"] != null && style["hidden"].toUpperCase() == "T") {
|
|
| 159 |
colHiddenStyle << i |
|
| 160 |
} |
|
| 161 |
} |
|
| 162 |
} |
|
| 163 |
} |
|
| 164 |
if (debug > 0) {
|
|
| 165 |
println "COL COL=$colColorStyle" |
|
| 166 |
println "COL SHP=$colShapeStyle" |
|
| 167 |
println "COL LAB=$colLabelStyle" |
|
| 168 |
println "COL FONT-SIZ=$colFontSizeStyle" |
|
| 169 |
println "COL SIZ=$colSizeStyle" |
|
| 170 |
println "COL VIZ=$colHiddenStyle" |
|
| 171 |
} |
|
| 172 |
|
|
| 173 |
|
|
| 174 |
|
|
| 175 |
// UPDATE THE CHART RENDERER |
|
| 176 |
|
|
| 177 |
def chartEditor = editor.getEditors()[0] |
|
| 178 |
def chartComposite = chartEditor.getComposite() |
|
| 179 |
|
|
| 180 |
ddebug = debug |
|
| 181 |
monitor.syncExec( new Runnable() {
|
|
| 182 |
public void run() {
|
|
| 183 |
println chartComposite |
|
| 184 |
def chart = chartEditor.getChart(); |
|
| 185 |
|
|
| 186 |
//println "chart: "+chart |
|
| 187 |
//println "Plot: "+chart.getPlot() |
|
| 188 |
//println "Dataset: "+chart.getPlot().getDataset() |
|
| 189 |
//println "Renderer: "+chart.getPlot().getRenderer() |
|
| 190 |
|
|
| 191 |
def renderer = new CAItemSelectionRenderer(ica, chart) {
|
|
| 192 |
Area EMPTYAREA = new Area() |
|
| 193 |
|
|
| 194 |
@Override |
|
| 195 |
public void initItemLabelGenerator() {
|
|
| 196 |
XYItemLabelGenerator generator = new XYItemLabelGenerator() {
|
|
| 197 |
|
|
| 198 |
@Override |
|
| 199 |
public String generateLabel(XYDataset dataset, int series, int item) {
|
|
| 200 |
if (series == 0 && rowHiddenStyle.contains(item)) {
|
|
| 201 |
if (ddebug > 1) println "HIDDING ROW LABEL '$item' '${rows[item]}'"
|
|
| 202 |
return "" |
|
| 203 |
} else if (series == 1 && colHiddenStyle.contains(item)) {
|
|
| 204 |
if (ddebug > 1) println "HIDDING COL LABEL '$item' '${cols[item]}'"
|
|
| 205 |
return "" |
|
| 206 |
} else if (series == 0 && rowLabelStyle.containsKey(item)) {
|
|
| 207 |
if (ddebug > 1) println "RENAME ROW LABEL '$item' '${rows[item]}' -> '${rowLabelStyle[item]}'"
|
|
| 208 |
return rowLabelStyle[item] |
|
| 209 |
} else if (series == 1 && colLabelStyle.containsKey(item)) {
|
|
| 210 |
if (ddebug > 1) println "RENAME COL LABEL '$item' '${cols[item]}' -> '${colLabelStyle[item]}'"
|
|
| 211 |
return colLabelStyle[item] |
|
| 212 |
} else {
|
|
| 213 |
CAXYDataset caDataset = (CAXYDataset) dataset; |
|
| 214 |
return caDataset.getLabel(series, item); |
|
| 215 |
} |
|
| 216 |
} |
|
| 217 |
}; |
|
| 218 |
|
|
| 219 |
this.setBaseItemLabelGenerator(generator); |
|
| 220 |
this.setBaseItemLabelsVisible(true); |
|
| 221 |
} |
|
| 222 |
|
|
| 223 |
@Override |
|
| 224 |
public Font getItemLabelFont(int series, int item) {
|
|
| 225 |
Font d = super.getItemLabelFont(series, item); |
|
| 226 |
if (series == 0 && rowFontSizeStyle.containsKey(item)) {
|
|
| 227 |
if (ddebug > 1) println "FIX ROW FONT-SIZE $item "+rows[item] |
|
| 228 |
return new Font(d.getFontName(), d.getStyle(), rowFontSizeStyle[item]); |
|
| 229 |
} else if (series == 1 && colFontSizeStyle.containsKey(item)) {
|
|
| 230 |
if (ddebug > 1) println "FIX COL FONT-SIZE $item "+cols[item] |
|
| 231 |
return new Font(d.getFontName(), d.getStyle(), colFontSizeStyle[item]); |
|
| 232 |
} else {
|
|
| 233 |
return d; |
|
| 234 |
} |
|
| 235 |
} |
|
| 236 |
|
|
| 237 |
@Override |
|
| 238 |
public Shape getItemShape(int series, int item) {
|
|
| 239 |
// Rows (series == 0), Cols (series == 1) |
|
| 240 |
if (series == 0 && rowHiddenStyle.contains(item)) {
|
|
| 241 |
return EMPTYAREA; |
|
| 242 |
} else if (series == 1 && colHiddenStyle.contains(item)) {
|
|
| 243 |
return EMPTYAREA; |
|
| 244 |
} else {
|
|
| 245 |
AffineTransform t = new AffineTransform(); |
|
| 246 |
Shape shape = super.getItemShape(series, item); |
|
| 247 |
if (series == 0 && rowSizeStyle.containsKey(item)) {
|
|
| 248 |
t.setToScale(rowSizeStyle.get(item), rowSizeStyle.get(item)); |
|
| 249 |
shape = t.createTransformedShape(shape); |
|
| 250 |
} else if (series == 1 && colSizeStyle.containsKey(item)) {
|
|
| 251 |
t.setToScale(colSizeStyle.get(item), colSizeStyle.get(item)); |
|
| 252 |
shape = t.createTransformedShape(shape); |
|
| 253 |
} |
|
| 254 |
return shape; |
|
| 255 |
} |
|
| 256 |
} |
|
| 257 |
|
|
| 258 |
@Override |
|
| 259 |
public Paint getItemPaint(int series, int item) {
|
|
| 260 |
if (series == 0 && rowColorStyle.containsKey(item)) {
|
|
| 261 |
return rowColorStyle.get(item); |
|
| 262 |
} else if (series == 1 && colColorStyle.containsKey(item)) {
|
|
| 263 |
return colColorStyle.get(item); |
|
| 264 |
} else {
|
|
| 265 |
return super.getItemPaint(series, item); |
|
| 266 |
} |
|
| 267 |
} |
|
| 268 |
}; |
|
| 269 |
|
|
| 270 |
def cp = editor.editors[0].getChart(); |
|
| 271 |
renderer.chart = cp |
|
| 272 |
renderer.setSeriesVisible(0, ica.isShowVariables()); // Rows |
|
| 273 |
renderer.setSeriesVisible(1, ica.isShowIndividuals()); // Columns |
|
| 274 |
chart.getXYPlot().setRenderer(renderer) |
|
| 275 |
|
|
| 276 |
ica.getChartCreator().getChartsEngine().getJFCTheme().apply(chart); // need to be call AFTER setRenderer() cause this method changes some renderering parameters |
|
| 277 |
} |
|
| 278 |
}); |
|
| tmp/org.txm.groovy.core/src/groovy/org/txm/macro/prototypes/stats/AFCWithStylesMacro.groovy (revision 2246) | ||
|---|---|---|
| 1 |
// STANDARD DECLARATIONS |
|
| 2 |
package org.txm.macro |
|
| 3 |
|
|
| 4 |
import org.kohsuke.args4j.* |
|
| 5 |
import groovy.transform.Field |
|
| 6 |
import org.txm.rcpapplication.swt.widget.parameters.* |
|
| 7 |
import org.txm.searchengine.cqp.clientExceptions.* |
|
| 8 |
import org.txm.searchengine.cqp.corpus.* |
|
| 9 |
import org.txm.searchengine.cqp.corpus.query.* |
|
| 10 |
import org.apache.commons.lang.time.StopWatch |
|
| 11 |
import java.util.Arrays |
|
| 12 |
import org.jfree.chart.renderer.xy.* |
|
| 13 |
import org.jfree.chart.renderer.* |
|
| 14 |
import org.jfree.chart.plot.* |
|
| 15 |
import org.jfree.data.xy.* |
|
| 16 |
import org.jfree.chart.axis.* |
|
| 17 |
import java.awt.*; |
|
| 18 |
import java.awt.geom.*; |
|
| 19 |
import org.jfree.chart.labels.* |
|
| 20 |
|
|
| 21 |
import org.txm.ca.core.chartsengine.jfreechart.themes.highcharts.renderers.* |
|
| 22 |
import org.txm.ca.rcp.editors.* |
|
| 23 |
import org.txm.libs.office.ReadODS |
|
| 24 |
import org.txm.ca.core.chartsengine.jfreechart.datasets.* |
|
| 25 |
import org.jfree.chart.renderer.AbstractRenderer |
|
| 26 |
|
|
| 27 |
println "editor: "+editor |
|
| 28 |
|
|
| 29 |
if (!(editor instanceof CAEditor)) {
|
|
| 30 |
println "editor is not a CA editor: $editor, Run the macro with F12 when the editor is selected :-)" |
|
| 31 |
return |
|
| 32 |
} |
|
| 33 |
|
|
| 34 |
@Field @Option(name="patternsODSFile", usage="The starting word", widget="FileOpen", required=true, def='patterns.ods') |
|
| 35 |
def patternsODSFile |
|
| 36 |
@Field @Option(name="debug", usage="Show internal variable content", widget="StringArray", metaVar="OFF ON ALL REALLY ALL", required=true, def="OFF") |
|
| 37 |
debug |
|
| 38 |
|
|
| 39 |
// Open the parameters input dialog box |
|
| 40 |
if (!ParametersDialog.open(this)) return; |
|
| 41 |
if (debug == "OFF") debug = 0; else if (debug == "ON") debug = 1; else if (debug == "ALL") debug = 2 else if (debug == "REALLY ALL") debug = 3 |
|
| 42 |
|
|
| 43 |
if (!patternsODSFile.exists()) {
|
|
| 44 |
println "Pattern file not found: $patternsODSFile" |
|
| 45 |
return false; |
|
| 46 |
} |
|
| 47 |
if (!patternsODSFile.isFile() || !patternsODSFile.getName().toLowerCase().endsWith(".ods")) {
|
|
| 48 |
println "Wrong pattern file: $patternsODSFile" |
|
| 49 |
return false; |
|
| 50 |
} |
|
| 51 |
|
|
| 52 |
def data = ReadODS.toTable(patternsODSFile, "rows") |
|
| 53 |
def keys = data[0] |
|
| 54 |
def row_styles = [:] // reformat data |
|
| 55 |
for (int i = 1 ; i < data.size() ; i++) {
|
|
| 56 |
def h = data[i] |
|
| 57 |
def style = [:] // create style entry |
|
| 58 |
String s = h[0]; |
|
| 59 |
row_styles[/$s/] = style // with a regexp pattern as key |
|
| 60 |
|
|
| 61 |
// fill the style |
|
| 62 |
for (int j = 1 ; j < h.size() ; j++) {
|
|
| 63 |
style[keys[j]] = h[j] |
|
| 64 |
} |
|
| 65 |
} |
|
| 66 |
if (debug > 0) {
|
|
| 67 |
println "ROW STYLES=$row_styles" |
|
| 68 |
} |
|
| 69 |
|
|
| 70 |
data = ReadODS.toTable(patternsODSFile, "cols") |
|
| 71 |
keys = data[0] |
|
| 72 |
def col_styles = [:] // reformat data |
|
| 73 |
for (int i = 1 ; i < data.size() ; i++) {
|
|
| 74 |
def h = data[i] |
|
| 75 |
def style = [:] // create style entry |
|
| 76 |
String s = h[0]; |
|
| 77 |
col_styles[/$s/] = style // with a regexp pattern as key |
|
| 78 |
|
|
| 79 |
// fill the style |
|
| 80 |
for (int j = 1 ; j < h.size() ; j++) {
|
|
| 81 |
style[keys[j]] = h[j] |
|
| 82 |
} |
|
| 83 |
} |
|
| 84 |
if (debug > 0) {
|
|
| 85 |
println "COL STYLES=$col_styles" |
|
| 86 |
} |
|
| 87 |
|
|
| 88 |
ica = editor.getCA() |
|
| 89 |
ca = ica.getCA() |
|
| 90 |
|
|
| 91 |
// http://txm.sourceforge.net/javadoc/TXM/TBX/org/txm/stat/engine/r/function/CA.html |
|
| 92 |
|
|
| 93 |
// SOME DATA |
|
| 94 |
rows = ica.getRowNames() |
|
| 95 |
rowsinfo = ica.getRowInfos() |
|
| 96 |
rowscos2 = ca.getRowCos2() |
|
| 97 |
cols = ica.getColNames() |
|
| 98 |
colssinfo = ica.getColInfos() |
|
| 99 |
colscos2 = ca.getColCos2() |
|
| 100 |
D1 = ica.getFirstDimension() -1; |
|
| 101 |
D2 = ica.getSecondDimension() -1; |
|
| 102 |
|
|
| 103 |
shapes = [:] |
|
| 104 |
shapes["square"] = AbstractRenderer.DEFAULT_SHAPE; |
|
| 105 |
shapes["circle"] = AbstractRenderer.DEFAULT_SHAPE; |
|
| 106 |
shapes["triangle"] = AbstractRenderer.DEFAULT_SHAPE; |
|
| 107 |
shapes["star"] = AbstractRenderer.DEFAULT_SHAPE; |
|
| 108 |
shapes["disk"] = AbstractRenderer.DEFAULT_SHAPE; |
|
| 109 |
|
|
| 110 |
// styles per col index in dataset |
|
| 111 |
// set col label |
|
| 112 |
colLabelStyle = new HashMap<Integer, String>(); |
|
| 113 |
// set col visibility |
|
| 114 |
colHiddenStyle = new HashSet<Integer>(); // true false |
|
| 115 |
// set col font size |
|
| 116 |
colFontSizeStyle = new HashMap<Integer, Integer>(); // 0.0 to 10.0 |
|
| 117 |
// set row font size |
|
| 118 |
colFontColorStyle = new HashMap<Integer, Color>(); // 0.0 to 10.0 |
|
| 119 |
// set row font size |
|
| 120 |
colFontFamillyStyle = new HashMap<Integer, String>(); // 0.0 to 10.0 |
|
| 121 |
// set col points size |
|
| 122 |
colPointSizeStyle = new HashMap<Integer, Double>(); // 0.0 to 10.0 |
|
| 123 |
// set col points RGBA color |
|
| 124 |
colPointColorStyle = new HashMap<Integer, Color>(); |
|
| 125 |
// set col points shape (circle, square, triangle, ... + color ? + size ?) -> expert |
|
| 126 |
colPointShapeStyle = new HashMap<Integer, Shape>(); // circle, square, triangle, etc. |
|
| 127 |
|
|
| 128 |
// set row label |
|
| 129 |
rowLabelStyle = new HashMap<Integer, String>(); |
|
| 130 |
// set row visibility |
|
| 131 |
rowHiddenStyle = new HashSet<Integer>(); // true false |
|
| 132 |
// set row font size |
|
| 133 |
rowFontSizeStyle = new HashMap<Integer, Integer>(); // 0.0 to 10.0 |
|
| 134 |
// set row font size |
|
| 135 |
rowFontColorStyle = new HashMap<Integer, Color>(); // 0.0 to 10.0 |
|
| 136 |
// set row font size |
|
| 137 |
rowFontFamillyStyle = new HashMap<Integer, String>(); // 0.0 to 10.0 |
|
| 138 |
// set row points size |
|
| 139 |
rowPointSizeStyle = new HashMap<Integer, Double>(); // 0.0 to 10.0 |
|
| 140 |
// set row points RGBA color |
|
| 141 |
rowPointColorStyle = new HashMap<Integer, Color>(); |
|
| 142 |
// set row points shape (circle, square, triangle, ... + color ? + size ?) -> expert |
|
| 143 |
rowPointShapeStyle = new HashMap<Integer, Shape>(); // circle, square, triangle, etc. |
|
| 144 |
|
|
| 145 |
// prepare col style data for the dataset |
|
| 146 |
for (int i = 0 ; i < cols.length ; i++) {
|
|
| 147 |
for (def p : col_styles.keySet()) {
|
|
| 148 |
if (cols[i] ==~ p) {
|
|
| 149 |
def style = col_styles[p] |
|
| 150 |
if (style["label"] != null && style["label"].length() > 0) {
|
|
| 151 |
colLabelStyle[i] = style["label"] |
|
| 152 |
} |
|
| 153 |
if (style["hidden"] != null && style["hidden"].toUpperCase() == "T") {
|
|
| 154 |
colHiddenStyle << i |
|
| 155 |
} |
|
| 156 |
if (style["point-size"] != null && style["point-size"].length() > 0) {
|
|
| 157 |
colPointSizeStyle[i] = Double.parseDouble(style["point-size"]) |
|
| 158 |
} |
|
| 159 |
if (style["point-color"] != null && style["point-color"].length() > 0 ) {
|
|
| 160 |
colPointColorStyle[i] = new Color(Integer.parseInt(style["point-color"]), false) |
|
| 161 |
} |
|
| 162 |
if (style["point-shape"] != null && shapes.containsKey(style["point-shape"])) {
|
|
| 163 |
colPointShapeStyle[i] = shapes[style["point-shape"]] |
|
| 164 |
} |
|
| 165 |
if (style["font-size"] != null && style["font-size"].length() > 0) {
|
|
| 166 |
colFontSizeStyle[i] = Integer.parseInt(style["font-size"]) |
|
| 167 |
} |
|
| 168 |
if (style["font-color"] != null && style["font-color"].length() > 0) {
|
|
| 169 |
colFontColorStyle[i] = Integer.parseInt(style["font-color"]) |
|
| 170 |
} |
|
| 171 |
if (style["font-familly"] != null && style["font-familly"].length() > 0) {
|
|
| 172 |
colFontFamillyStyle[i] = style["font-familly"] |
|
| 173 |
} |
|
| 174 |
} |
|
| 175 |
} |
|
| 176 |
} |
|
| 177 |
if (debug > 0) {
|
|
| 178 |
println "COL COL=$colPointColorStyle" |
|
| 179 |
println "COL SHP=$colPointShapeStyle" |
|
| 180 |
println "COL LAB=$colLabelStyle" |
|
| 181 |
println "COL FONT-SIZ=$colFontSizeStyle" |
|
| 182 |
println "COL SIZ=$colPointSizeStyle" |
|
| 183 |
println "COL VIZ=$colHiddenStyle" |
|
| 184 |
} |
|
| 185 |
|
|
| 186 |
// prepare row style data for the dataset |
|
| 187 |
for (int i = 0 ; i < rows.length ; i++) {
|
|
| 188 |
for (def p : row_styles.keySet()) {
|
|
| 189 |
if (rows[i] ==~ p) {
|
|
| 190 |
def style = row_styles[p] |
|
| 191 |
if (style["hidden"] != null && style["hidden"].toUpperCase() == "T") {
|
|
| 192 |
rowHiddenStyle << i |
|
| 193 |
} |
|
| 194 |
if (style["label"] != null && style["label"].length() > 0) {
|
|
| 195 |
rowLabelStyle[i] = style["label"] |
|
| 196 |
} |
|
| 197 |
if (style["point-size"] != null && style["point-size"].length() > 0) {
|
|
| 198 |
rowPointSizeStyle[i] = Double.parseDouble(style["point-size"]) |
|
| 199 |
} |
|
| 200 |
if (style["point-color"] != null && style["point-color"].length() > 0 ) {
|
|
| 201 |
rowPointColorStyle[i] = new Color(Integer.parseInt(style["point-color"]), false) |
|
| 202 |
} |
|
| 203 |
if (style["point-shape"] != null && shapes.containsKey(style["point-shape"])) {
|
|
| 204 |
rowPointShapeStyle[i] = shapes[style["point-shape"]] |
|
| 205 |
} |
|
| 206 |
if (style["font-size"] != null && style["font-size"].length() > 0) {
|
|
| 207 |
rowFontSizeStyle[i] = Integer.parseInt(style["font-size"]) |
|
| 208 |
} |
|
| 209 |
if (style["font-color"] != null && style["font-color"].length() > 0) {
|
|
| 210 |
rowFontColorStyle[i] = Integer.parseInt(style["font-color"]) |
|
| 211 |
} |
|
| 212 |
if (style["font-familly"] != null && style["font-familly"].length() > 0) {
|
|
| 213 |
rowFontFamillyStyle[i] = style["font-familly"] |
|
| 214 |
} |
|
| 215 |
} |
|
| 216 |
} |
|
| 217 |
} |
|
| 218 |
if (debug > 0) {
|
|
| 219 |
println "ROW COL=$rowPointColorStyle" |
|
| 220 |
println "ROW SHP=$rowPointShapeStyle" |
|
| 221 |
println "ROW LAB=$rowLabelStyle" |
|
| 222 |
println "ROW FONT-SIZ=$rowFontSizeStyle" |
|
| 223 |
println "ROW SIZ=$rowPointSizeStyle" |
|
| 224 |
println "ROW VIZ=$rowHiddenStyle" |
|
| 225 |
} |
|
| 226 |
|
|
| 227 |
|
|
| 228 |
// UPDATE THE CHART RENDERER |
|
| 229 |
|
|
| 230 |
def chartEditor = editor.getEditors()[0] |
|
| 231 |
def chartComposite = chartEditor.getComposite() |
|
| 232 |
|
|
| 233 |
ddebug = debug |
|
| 234 |
monitor.syncExec( new Runnable() {
|
|
| 235 |
public void run() {
|
|
| 236 |
println chartComposite |
|
| 237 |
def chart = chartEditor.getChart(); |
|
| 238 |
|
|
| 239 |
//println "chart: "+chart |
|
| 240 |
//println "Plot: "+chart.getPlot() |
|
| 241 |
//println "Dataset: "+chart.getPlot().getDataset() |
|
| 242 |
//println "Renderer: "+chart.getPlot().getRenderer() |
|
| 243 |
|
|
| 244 |
def renderer = new CAItemSelectionRenderer(ica, chart) {
|
|
| 245 |
Area EMPTYAREA = new Area() |
|
| 246 |
|
|
| 247 |
@Override |
|
| 248 |
public void initItemLabelGenerator() {
|
|
| 249 |
XYItemLabelGenerator generator = new XYItemLabelGenerator() {
|
|
| 250 |
|
|
| 251 |
@Override |
|
| 252 |
public String generateLabel(XYDataset dataset, int series, int item) {
|
|
| 253 |
if (series == 0 && rowHiddenStyle.contains(item)) {
|
|
| 254 |
if (ddebug > 1) println "HIDDING ROW LABEL '$item' '${rows[item]}'"
|
|
| 255 |
return "" |
|
| 256 |
} else if (series == 1 && colHiddenStyle.contains(item)) {
|
|
| 257 |
if (ddebug > 1) println "HIDDING COL LABEL '$item' '${cols[item]}'"
|
|
| 258 |
return "" |
|
| 259 |
} else if (series == 0 && rowLabelStyle.containsKey(item)) {
|
|
| 260 |
if (ddebug > 1) println "RENAME ROW LABEL '$item' '${rows[item]}' -> '${rowLabelStyle[item]}'"
|
|
| 261 |
return rowLabelStyle[item] |
|
| 262 |
} else if (series == 1 && colLabelStyle.containsKey(item)) {
|
|
| 263 |
if (ddebug > 1) println "RENAME COL LABEL '$item' '${cols[item]}' -> '${colLabelStyle[item]}'"
|
|
| 264 |
return colLabelStyle[item] |
|
| 265 |
} else {
|
|
| 266 |
CAXYDataset caDataset = (CAXYDataset) dataset; |
|
| 267 |
return caDataset.getLabel(series, item); |
|
| 268 |
} |
|
| 269 |
} |
|
| 270 |
}; |
|
| 271 |
|
|
| 272 |
this.setBaseItemLabelGenerator(generator); |
|
| 273 |
this.setBaseItemLabelsVisible(true); |
|
| 274 |
} |
|
| 275 |
|
|
| 276 |
@Override |
|
| 277 |
public Font getItemLabelFont(int series, int item) {
|
|
| 278 |
Font d = super.getItemLabelFont(series, item); |
|
| 279 |
|
|
| 280 |
if (series == 0 && rowFontSizeStyle.containsKey(item)) {
|
|
| 281 |
if (ddebug > 1) println "FIX ROW FONT-SIZE $item ${rows[item]} -> ${rowFontSizeStyle[item]}"
|
|
| 282 |
d = new Font(d.getFontName(), d.getStyle(), rowFontSizeStyle[item]); |
|
| 283 |
} else if (series == 1 && colFontSizeStyle.containsKey(item)) {
|
|
| 284 |
if (ddebug > 1) println "FIX COL FONT-SIZE $item ${cols[item]} -> ${colFontSizeStyle[item]}"
|
|
| 285 |
d = new Font(d.getFontName(), d.getStyle(), colFontSizeStyle[item]); |
|
| 286 |
} |
|
| 287 |
|
|
| 288 |
if (series == 0 && rowFontFamillyStyle.containsKey(item)) {
|
|
| 289 |
if (ddebug > 1) println "FIX ROW FONT-FAMILLY $item ${rows[item]} -> ${rowFontFamillyStyle[item]}"
|
|
| 290 |
d = new Font(rowFontFamillyStyle[item], d.getStyle(), d.getSize()); |
|
| 291 |
} else if (series == 1 && colFontFamillyStyle.containsKey(item)) {
|
|
| 292 |
if (ddebug > 1) println "FIX COL FONT-FAMILLY $item ${cols[item]} -> ${colFontFamillyStyle[item]}"
|
|
| 293 |
d = new Font(colFontFamillyStyle[item], d.getStyle(), d.getSize()); |
|
| 294 |
} |
|
| 295 |
|
|
| 296 |
return d; |
|
| 297 |
} |
|
| 298 |
|
|
| 299 |
@Override |
|
| 300 |
public Shape getItemShape(int series, int item) {
|
|
| 301 |
// Rows (series == 0), Cols (series == 1) |
|
| 302 |
if (series == 0 && rowHiddenStyle.contains(item)) {
|
|
| 303 |
return EMPTYAREA; |
|
| 304 |
} else if (series == 1 && colHiddenStyle.contains(item)) {
|
|
| 305 |
return EMPTYAREA; |
|
| 306 |
} else {
|
|
| 307 |
AffineTransform t = new AffineTransform(); |
|
| 308 |
Shape shape = super.getItemShape(series, item); |
|
| 309 |
if (series == 0 && rowPointSizeStyle.containsKey(item)) {
|
|
| 310 |
if (ddebug > 1) println "FIX ROW POINT SIZE $item ${rows[item]} -> ${rowPointSizeStyle[item]}"
|
|
| 311 |
t.setToScale(rowPointSizeStyle.get(item), rowPointSizeStyle.get(item)); |
|
| 312 |
shape = t.createTransformedShape(shape); |
|
| 313 |
} else if (series == 1 && colPointSizeStyle.containsKey(item)) {
|
|
| 314 |
if (ddebug > 1) println "FIX COL POINT SIZE $item ${cols[item]} -> ${colPointSizeStyle[item]}"
|
|
| 315 |
t.setToScale(colPointSizeStyle.get(item), colPointSizeStyle.get(item)); |
|
| 316 |
shape = t.createTransformedShape(shape); |
|
| 317 |
} |
|
| 318 |
return shape; |
|
| 319 |
} |
|
| 320 |
} |
|
| 321 |
|
|
| 322 |
@Override |
|
| 323 |
public Paint getItemPaint(int series, int item) {
|
|
| 324 |
if (series == 0 && rowPointColorStyle.containsKey(item)) {
|
|
| 325 |
if (ddebug > 1) println "FIX ROW POINT COLOR $item ${rows[item]} -> ${rowPointColorStyle[item]}"
|
|
| 326 |
return rowPointColorStyle.get(item); |
|
| 327 |
} else if (series == 1 && colPointColorStyle.containsKey(item)) {
|
|
| 328 |
if (ddebug > 1) println "FIX COL POINT COLOR $item ${cols[item]} -> ${colPointColorStyle[item]}"
|
|
| 329 |
return colPointColorStyle.get(item); |
|
| 330 |
} else {
|
|
| 331 |
return super.getItemPaint(series, item); |
|
| 332 |
} |
|
| 333 |
} |
|
| 334 |
}; |
|
| 335 |
|
|
| 336 |
def cp = editor.editors[0].getChart(); |
|
| 337 |
renderer.chart = cp |
|
| 338 |
renderer.setSeriesVisible(0, ica.isShowVariables()); // Rows |
|
| 339 |
renderer.setSeriesVisible(1, ica.isShowIndividuals()); // Columns |
|
| 340 |
chart.getXYPlot().setRenderer(renderer) |
|
| 341 |
|
|
| 342 |
ica.getChartCreator().getChartsEngine().getJFCTheme().apply(chart); // need to be call AFTER setRenderer() cause this method changes some renderering parameters |
|
| 343 |
} |
|
| 344 |
}); |
|
| tmp/org.txm.groovy.core/src/groovy/org/txm/macro/prototypes/commands/PrunePartitionMacro.groovy (revision 2246) | ||
|---|---|---|
| 1 |
// STANDARD DECLARATIONS |
|
| 2 |
package org.txm.macro |
|
| 3 |
|
|
| 4 |
import org.kohsuke.args4j.* |
|
| 5 |
import groovy.transform.Field |
|
| 6 |
import org.txm.rcp.swt.widget.parameters.* |
|
| 7 |
import org.txm.searchengine.cqp.corpus.* |
|
| 8 |
|
|
| 9 |
// BEGINNING OF PARAMETERS |
|
| 10 |
|
|
| 11 |
|
|
| 12 |
@Field @Option(name="min", usage="F min", widget="Float", required=false, def="18") |
|
| 13 |
def min |
|
| 14 |
|
|
| 15 |
@Field @Option(name="relative", usage="min is a % of the total frequency", widget="Boolean", required=false, def="false") |
|
| 16 |
def relative |
|
| 17 |
|
|
| 18 |
@Field @Option(name="doIt", usage="delete the selected parts", widget="Boolean", required=false, def="false") |
|
| 19 |
def doIt |
|
| 20 |
|
|
| 21 |
@Field @Option(name="debug", usage="show debug messages", widget="Boolean", required=false, def="false") |
|
| 22 |
def debug |
|
| 23 |
|
|
| 24 |
// Open the parameters input dialog box |
|
| 25 |
if (!ParametersDialog.open(this)) return; |
|
| 26 |
|
|
| 27 |
// END OF PARAMETERS |
|
| 28 |
|
|
| 29 |
if (!(corpusViewSelection instanceof Partition)) {
|
|
| 30 |
println "Aborting, the selection is not a Partition: $corpusViewSelection" |
|
| 31 |
return |
|
| 32 |
} |
|
| 33 |
|
|
| 34 |
def partition = corpusViewSelection |
|
| 35 |
partition.compute(false) // ensure parts are ready to use |
|
| 36 |
|
|
| 37 |
int F = 0; |
|
| 38 |
for (def part : partition.getParts()) {
|
|
| 39 |
F += part.getSize(); |
|
| 40 |
} |
|
| 41 |
if (debug) println "F=$F" |
|
| 42 |
if (relative) {
|
|
| 43 |
min = (F*min)/100 |
|
| 44 |
} |
|
| 45 |
if (debug) println "F min threshold=$min" |
|
| 46 |
|
|
| 47 |
def toDelete = [] |
|
| 48 |
for (def part : partition.getParts()) {
|
|
| 49 |
if (part.getSize() < min) {
|
|
| 50 |
toDelete << part |
|
| 51 |
} |
|
| 52 |
} |
|
| 53 |
if (toDelete.size() > 0) {
|
|
| 54 |
println (doIt?"Deleting ${toDelete.size()} parts: $toDelete":"Selected parts $toDelete")
|
|
| 55 |
for (def part : toDelete) {
|
|
| 56 |
if (doIt) part.delete() |
|
| 57 |
} |
|
| 58 |
} |
|
| 59 |
println "Done" |
|
| tmp/org.txm.groovy.core/src/groovy/org/txm/macro/prototypes/importer/XTZImporterMacro.groovy (revision 2246) | ||
|---|---|---|
| 230 | 230 |
//get metadatas values from CSV |
| 231 | 231 |
Metadatas metadatas; // text metadatas |
| 232 | 232 |
|
| 233 |
println "Trying to read metadatas from: "+allMetadataFile
|
|
| 233 |
println "Trying to read metadata from: "+allMetadataFile |
|
| 234 | 234 |
if (MONITOR != null && MONITOR.isCanceled()) { return MONITOR.done(); }
|
| 235 | 235 |
if (allMetadataFile.exists()) {
|
| 236 | 236 |
File copy = new File(binDir, allMetadataFile.getName()) |
| tmp/org.txm.groovy.core/src/groovy/org/txm/scripts/clix/treetagger-wrapper-definition.xml (revision 2246) | ||
|---|---|---|
| 9 | 9 |
<arg state="optional" type="float" name="threshold" desc="Print all tags of a word with a probability higher than p times the largest probability"/> |
| 10 | 10 |
<arg state="optional" type="none" name="prob" desc="Print tag probabilities"/> |
| 11 | 11 |
<arg state="optional" type="none" name="ignore-prefix" desc=" Ignore prefix when guessing pos for unknown words"/> |
| 12 |
<arg state="optional" type="none" name="no-unknown" desc="Print the token rather than [unknown] for unknown lemmas"/>
|
|
| 12 |
<arg state="optional" type="none" name="no-unknown" desc="Print the token rather than [unknown] for unknown lemma"/> |
|
| 13 | 13 |
<arg state="optional" type="none" name="cap-heuristics" desc="Look up unknown capitalized words in the list of lower-case words"/> |
| 14 | 14 |
<arg state="optional" type="none" name="hyphen-heuristics" desc="Turn on the heuristics fur guessing the parts of speech of unknown hyphenated words"/> |
| 15 | 15 |
<arg state="optional" type="none" name="quiet" desc="quiet mode"/> |
| tmp/org.txm.groovy.core/src/groovy/org/txm/scripts/importer/cqp/pager.groovy (revision 2246) | ||
|---|---|---|
| 183 | 183 |
|
| 184 | 184 |
pagedWriter = new OutputStreamWriter(new BufferedOutputStream(new FileOutputStream(outfile)) , "UTF-8"); |
| 185 | 185 |
pagedWriter.write("<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n");
|
| 186 |
pagedWriter.write("<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.0 Transitional//EN\" \"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">\n")
|
|
| 186 |
pagedWriter.write("<!DOCTYPE html>\n")
|
|
| 187 | 187 |
pagedWriter.write("<html>");
|
| 188 | 188 |
pagedWriter.write("<head>");
|
| 189 | 189 |
pagedWriter.write("<title>"+basename.toUpperCase()+" $txtname Edition - Page "+pagecount+"</title>");
|
| tmp/org.txm.groovy.core/src/groovy/org/txm/scripts/importer/xtz/xtzLoader.groovy (revision 2246) | ||
|---|---|---|
| 46 | 46 |
try {project=projectBinding;MONITOR=monitor} catch (Exception)
|
| 47 | 47 |
{ }
|
| 48 | 48 |
if (project == null) { println "no project set. Aborting"; return; }
|
| 49 |
|
|
| 50 | 49 |
XTZImport i = new XTZImport(project); |
| 50 |
i.setMonitor(monitor) |
|
| 51 | 51 |
/* |
| 52 | 52 |
* To customize the XTZ import, replace the importer, compiler, annotater or pager objects before calling process() |
| 53 | 53 |
i.importer = new XTZImporter(i) |
| tmp/org.txm.groovy.core/src/groovy/org/txm/scripts/importer/xtz/XTZCompiler.groovy (revision 2246) | ||
|---|---|---|
| 6 | 6 |
import org.txm.scripts.importer.SAttributesListener |
| 7 | 7 |
import org.txm.importer.cwb.* |
| 8 | 8 |
import org.txm.utils.ConsoleProgressBar |
| 9 |
import org.txm.utils.logger.Log |
|
| 9 | 10 |
import org.txm.core.preferences.TXMPreferences |
| 10 | 11 |
import org.txm.core.preferences.TBXPreferences |
| 11 | 12 |
import org.txm.libs.cqp.CQPLibPreferences |
| ... | ... | |
| 19 | 20 |
|
| 20 | 21 |
SAttributesListener sattrsListener; // store scanned structures |
| 21 | 22 |
private def anatypes = new HashSet<String>() // store scanned word attributes |
| 22 |
|
|
| 23 |
|
|
| 23 | 24 |
String regPath; |
| 24 | 25 |
String corpusname; |
| 25 | 26 |
String wtag; |
| 26 |
|
|
| 27 |
|
|
| 27 | 28 |
boolean doNormalizeAttributeValues = false; |
| 28 | 29 |
boolean doNormalizeAnaValues = true; |
| 29 |
|
|
| 30 |
|
|
| 30 | 31 |
public XTZCompiler(ImportModule module) {
|
| 31 | 32 |
super(module); |
| 32 | 33 |
|
| 33 | 34 |
corpusname = module.getProject().getName(); |
| 34 | 35 |
regPath = module.getBinaryDirectory().getAbsolutePath() + "/registry/"+corpusname.toLowerCase() |
| 35 |
|
|
| 36 |
|
|
| 36 | 37 |
wtag = module.getProject().getTokenizerWordElement(); |
| 37 |
|
|
| 38 |
|
|
| 38 | 39 |
doNormalizeAttributeValues = "true".equals(module.getProject().getPreferencesScope().getNode("import").get(TBXPreferences.NORMALISEATTRIBUTEVALUES, "false"))
|
| 39 | 40 |
doNormalizeAnaValues = "true".equals(module.getProject().getPreferencesScope().getNode("import").get(TBXPreferences.NORMALISEANAVALUES, "false"))
|
| 40 | 41 |
} |
| 41 | 42 |
|
| 42 |
public void process(ArrayList<File> files) {
|
|
| 43 |
super.process(files); // set member |
|
| 44 |
|
|
| 45 |
if (files == null) files = inputDirectory.listFiles(); |
|
| 46 |
|
|
| 43 |
@Override |
|
| 44 |
public void process(List<String> orderedTextIDs) {
|
|
| 45 |
super.process(orderedTextIDs); // set member |
|
| 46 |
|
|
| 47 |
if (orderedTextIDs == null) orderedTextIDs = module.getProject().getTextsID() ; |
|
| 48 |
|
|
| 47 | 49 |
Project project = module.getProject(); |
| 48 | 50 |
CorpusBuild corpus = project.getCorpusBuild(project.getName(), MainCorpus.class); |
| 49 | 51 |
if (corpus != null) {
|
| ... | ... | |
| 58 | 60 |
corpus.setName(project.getName()); |
| 59 | 61 |
} |
| 60 | 62 |
corpus.setDescription("Built with the XTZ import module");
|
| 61 |
|
|
| 63 |
|
|
| 62 | 64 |
if (!doScanStep()) return; |
| 63 | 65 |
if (!doCQPStep()) return; |
| 64 | 66 |
if (!doCWBEncodeStep()) return; |
| 65 | 67 |
if (!doCWBMakeAllStep()) return; |
| 66 |
|
|
| 67 |
if (module.getProject().getCleanAfterBuild()) {
|
|
| 68 |
|
|
| 69 |
if (module.getProject().getCleanAfterBuild() && !module.getProject().getDoUpdate()) {
|
|
| 68 | 70 |
new File(module.getBinaryDirectory(), "cqp").deleteDir() |
| 69 | 71 |
} |
| 70 |
|
|
| 72 |
|
|
| 71 | 73 |
isSuccessFul = true; |
| 72 | 74 |
} |
| 73 | 75 |
|
| ... | ... | |
| 75 | 77 |
* Scan all XML-TXM files to find out structures and word properties |
| 76 | 78 |
*/ |
| 77 | 79 |
public boolean doScanStep() {
|
| 78 |
// get all anatypes
|
|
| 80 |
// get all anatypes |
|
| 79 | 81 |
sattrsListener = SAttributesListener.scanFiles(inputDirectory, wtag) |
| 80 |
println "-- Listing structures&properties to create for "+files.size()+" XML-TXM files..." |
|
| 81 |
ConsoleProgressBar cpb = new ConsoleProgressBar(files.size()) |
|
| 82 |
for (File f : files) {
|
|
| 82 |
def texts = module.getProject().getTexts() |
|
| 83 |
println "-- Listing structures&properties to create for "+texts.size()+" texts..." |
|
| 84 |
ConsoleProgressBar cpb = new ConsoleProgressBar(texts.size()) |
|
| 85 |
for (Text t : texts) {
|
|
| 83 | 86 |
try {
|
| 84 | 87 |
cpb.tick(); |
| 85 |
getAnaTypes(f)
|
|
| 88 |
getAnaTypes(t.getXMLTXMFile())
|
|
| 86 | 89 |
} catch (Exception e) {
|
| 87 |
println "Error while processing $f text: "+e
|
|
| 90 |
println "Error while processing $t text XML-TXM file : "+t.getSource()+". Error: "+e
|
|
| 88 | 91 |
e.printStackTrace(); |
| 89 | 92 |
return false; |
| 90 | 93 |
} |
| ... | ... | |
| 92 | 95 |
println "" |
| 93 | 96 |
return true; |
| 94 | 97 |
} |
| 95 |
|
|
| 98 |
|
|
| 96 | 99 |
private void getAnaTypes(File xmlFile) {
|
| 97 | 100 |
def inputData = xmlFile.toURI().toURL().openStream(); |
| 98 | 101 |
def factory = XMLInputFactory.newInstance(); |
| ... | ... | |
| 115 | 118 |
} else if (event == XMLStreamConstants.END_ELEMENT) { // start elem
|
| 116 | 119 |
if (wtag.equals(parser.getLocalName())) {
|
| 117 | 120 |
start = false; |
| 118 |
}
|
|
| 121 |
} |
|
| 119 | 122 |
} |
| 120 | 123 |
} |
| 121 |
|
|
| 124 |
|
|
| 122 | 125 |
if (parser != null) parser.close(); |
| 123 | 126 |
if (inputData != null) inputData.close(); |
| 124 |
|
|
| 125 |
// for (String type : types) |
|
| 126 |
// if (!anatypes.contains(type)) |
|
| 127 |
// anatypes << type |
|
| 127 |
|
|
| 128 |
// for (String type : types)
|
|
| 129 |
// if (!anatypes.contains(type))
|
|
| 130 |
// anatypes << type
|
|
| 128 | 131 |
} |
| 129 | 132 |
|
| 130 | 133 |
def cqpFiles = [] |
| 134 |
int cqpFilesUpdated = 0; |
|
| 131 | 135 |
public boolean doCQPStep() {
|
| 132 | 136 |
println "-- Building CQP files $inputDirectory..." |
| 133 | 137 |
cqpDirectory.mkdir(); // if not created |
| 134 |
|
|
| 135 |
ConsoleProgressBar cpb = new ConsoleProgressBar(files.size()) |
|
| 136 |
for (File xmlFile : files) {
|
|
| 138 |
|
|
| 139 |
def texts = module.getProject().getTexts() |
|
| 140 |
ConsoleProgressBar cpb = new ConsoleProgressBar(texts.size()) |
|
| 141 |
cqpFilesUpdated = 0; |
|
| 142 |
for (Text text : texts) {
|
|
| 137 | 143 |
cpb.tick(); |
| 138 |
String textname = xmlFile.getName(); |
|
| 139 |
int idx = textname.lastIndexOf(".")
|
|
| 140 |
if (idx > 0) textname = textname.substring(0, idx)
|
|
| 141 |
|
|
| 144 |
|
|
| 145 |
File xmlFile = text.getXMLTXMFile()
|
|
| 146 |
String textname = text.getName()
|
|
| 147 |
|
|
| 142 | 148 |
File cqpFile = new File(cqpDirectory, textname + ".cqp") |
| 143 | 149 |
cqpFiles << cqpFile |
| 144 |
// skip step if cqpFile is more recent than xmlFile |
|
| 145 |
if (cqpFile.exists() && cqpFile.lastModified() >= xmlFile.lastModified()) continue; |
|
| 150 |
|
|
| 151 |
// skip step if cqpFile exists AND is more recent than the XML-TXM File |
|
| 152 |
boolean mustBuild = false; |
|
| 153 |
if (!cqpFile.exists() || xmlFile.lastModified() >= cqpFile.lastModified()) {
|
|
| 154 |
mustBuild = true |
|
| 155 |
} |
|
| 156 |
|
|
| 157 |
if (!text.isDirty() && !mustBuild) {
|
|
| 158 |
Log.finer("skipping .cqp step of $text");
|
|
| 159 |
continue |
|
| 160 |
} |
|
| 146 | 161 |
|
| 162 |
cqpFilesUpdated++ |
|
| 163 |
|
|
| 147 | 164 |
XTZCompilerStep step = new XTZCompilerStep(xmlFile, cqpFile, textname, corpusname, "default", anatypes, wtag) |
| 148 | 165 |
step.setNormalizeAnaValues(doNormalizeAnaValues) |
| 149 | 166 |
step.setNormalizeAttributeValues(doNormalizeAttributeValues) |
| ... | ... | |
| 160 | 177 |
println "-- Running cwb-encode..." |
| 161 | 178 |
CwbEncode cwbEn = new CwbEncode() |
| 162 | 179 |
cwbEn.setDebug(debug) |
| 163 |
|
|
| 180 |
|
|
| 164 | 181 |
List<String> pargs = [] |
| 165 | 182 |
pargs.add("id")
|
| 166 | 183 |
for (String ana : anatypes) |
| ... | ... | |
| 175 | 192 |
println structs |
| 176 | 193 |
println structsProf |
| 177 | 194 |
} |
| 178 |
|
|
| 195 |
|
|
| 179 | 196 |
List<String> sargs = new ArrayList<String>() |
| 180 | 197 |
def tmpTextAttrs = [] |
| 181 | 198 |
for (String name : structs.keySet()) {
|
| ... | ... | |
| 188 | 205 |
String concat = name+":"+structsProf.get(name); // append the depth |
| 189 | 206 |
for (String attributeName : structs.get(name)) // append the attributes |
| 190 | 207 |
concat += "+"+attributeName.toLowerCase(); |
| 191 |
|
|
| 208 |
|
|
| 192 | 209 |
if (structs.get(name).size() == 0) {
|
| 193 | 210 |
concat += "+n"; |
| 194 | 211 |
} else {
|
| 195 | 212 |
if (!structs.get(name).contains("n"))
|
| 196 | 213 |
concat += "+n" |
| 197 | 214 |
} |
| 198 |
|
|
| 215 |
|
|
| 199 | 216 |
if ((name == "p" || name == "body" || name == "back" || name == "front") |
| 200 |
&& !concat.contains("+n+") && !concat.endsWith("+n"))
|
|
| 217 |
&& !concat.contains("+n+") && !concat.endsWith("+n"))
|
|
| 201 | 218 |
concat += "+n" |
| 202 |
|
|
| 219 |
|
|
| 203 | 220 |
sargs.add(concat) |
| 204 | 221 |
} |
| 205 | 222 |
|
| ... | ... | |
| 225 | 242 |
println "Fail to write the master cqp file: "+allcqpFile |
| 226 | 243 |
return false; |
| 227 | 244 |
} |
| 228 |
|
|
| 245 |
|
|
| 229 | 246 |
if (!cwbEn.run(outputDirectory.getAbsolutePath() + "/$corpusname", |
| 230 |
allcqpFile.getAbsolutePath(),
|
|
| 231 |
regPath, pAttributes, sAttributes, false)) {
|
|
| 247 |
allcqpFile.getAbsolutePath(), |
|
| 248 |
regPath, pAttributes, sAttributes, false)) {
|
|
| 232 | 249 |
println "** cwb-encode did not ends well. Activate finer logs to see details." |
| 233 | 250 |
return false; |
| 234 | 251 |
} |
| 235 |
|
|
| 252 |
|
|
| 236 | 253 |
allcqpFile.delete(); // clean |
| 237 | 254 |
} catch (Exception e) {
|
| 238 | 255 |
println "Error while running cwb-encode: "+e |
| 239 | 256 |
e.printStackTrace() |
| 240 |
allcqpFile.delete(); // clean
|
|
| 257 |
allcqpFile.delete(); // clean |
|
| 241 | 258 |
return false; |
| 242 | 259 |
} |
| 243 | 260 |
println "" |
| ... | ... | |
| 258 | 275 |
println "** cwb-makeall did not ends well. Activate finer logs to see details." |
| 259 | 276 |
return false; |
| 260 | 277 |
} |
| 261 |
|
|
| 278 |
|
|
| 262 | 279 |
// remove milestones from CWB registry and data files |
| 263 | 280 |
FixMilestoneDeclarations fm = new FixMilestoneDeclarations( |
| 264 |
new File(regPath), new File(outputDirectory.getAbsolutePath(), corpusname)); |
|
| 281 |
new File(regPath), new File(outputDirectory.getAbsolutePath(), corpusname));
|
|
| 265 | 282 |
if (!fm.process()) {
|
| 266 | 283 |
println "Fail to verify&fix milestone declarations" |
| 267 | 284 |
return false |
| tmp/org.txm.groovy.core/src/groovy/org/txm/scripts/importer/xtz/XTZImport.groovy (revision 2246) | ||
|---|---|---|
| 36 | 36 |
} |
| 37 | 37 |
|
| 38 | 38 |
@Override |
| 39 |
protected ArrayList<File> getTXMFilesOrder() {
|
|
| 39 |
protected ArrayList<String> getTXMFilesOrder() {
|
|
| 40 | 40 |
//System.out.println("XTZ FILES ORDER");
|
| 41 | 41 |
if (importer == null) {
|
| 42 | 42 |
println "no importer step, using default text order" |
| ... | ... | |
| 55 | 55 |
} |
| 56 | 56 |
}))); |
| 57 | 57 |
|
| 58 |
final HashMap<File, String> textorder = new HashMap<File, String>(); |
|
| 59 |
for (File f : files) {
|
|
| 60 |
HashMap<String, String> m = metadata.getTextMetadata(f); |
|
| 61 |
if (m != null && m.containsKey("textorder")) textorder[f] = m["textorder"];
|
|
| 58 |
// fill sort data map |
|
| 59 |
final HashMap<String, String> textorder = new HashMap<String, String>(); |
|
| 60 |
for (String t : metadata.keySet()) {
|
|
| 61 |
def ti = metadata.get(t) |
|
| 62 |
for (org.txm.metadatas.Entry e : ti) {
|
|
| 63 |
if ("textorder".equals(e.getId())) {
|
|
| 64 |
textorder[t] = ti.get("textorder")
|
|
| 65 |
} |
|
| 66 |
} |
|
| 62 | 67 |
} |
| 68 |
|
|
| 63 | 69 |
println "Sorting texts using 'textorder' metadata values: "+textorder |
| 64 |
Collections.sort(files, new Comparator<File>() {
|
|
| 65 |
public int compare(File f1, File f2) {
|
|
| 70 |
def texts = project.getTextsID(); |
|
| 71 |
Collections.sort(texts, new Comparator<String>() {
|
|
| 72 |
public int compare(String f1, String f2) {
|
|
| 66 | 73 |
String o1 = textorder[f1]; |
| 67 | 74 |
String o2 = textorder[f2]; |
| 68 | 75 |
if (o1 == null && o2 == null) {
|
| 69 |
return f1.getName().compareTo(f2.getName());
|
|
| 76 |
return f1.compareTo(f2);
|
|
| 70 | 77 |
} else if (o1 == null) {
|
| 71 | 78 |
return 1 |
| 72 | 79 |
} else if (o2 == null) {
|
| 73 | 80 |
return -1 |
| 74 | 81 |
} else {
|
| 75 | 82 |
int c = o1.compareTo(o2); |
| 76 |
if (c == 0) return f1.getName().compareTo(f2.getName());
|
|
| 83 |
if (c == 0) return f1.compareTo(f2);
|
|
| 77 | 84 |
else return c; |
| 78 | 85 |
} |
| 79 | 86 |
} |
| tmp/org.txm.groovy.core/src/groovy/org/txm/scripts/importer/xtz/XTZPager.groovy (revision 2246) | ||
|---|---|---|
| 13 | 13 |
import org.txm.utils.i18n.* |
| 14 | 14 |
import org.txm.importer.xtz.* |
| 15 | 15 |
import javax.xml.stream.* |
| 16 |
|
|
| 16 | 17 |
import org.txm.objects.* |
| 17 | 18 |
import org.txm.importer.ApplyXsl2 |
| 19 |
import org.txm.utils.logger.Log |
|
| 18 | 20 |
|
| 19 | 21 |
class XTZPager extends Pager {
|
| 20 | 22 |
|
| ... | ... | |
| 43 | 45 |
imagesDirectory = new File(module.getSourceDirectory(), "images") |
| 44 | 46 |
} |
| 45 | 47 |
|
| 46 |
public void process(ArrayList<File> files) {
|
|
| 47 |
super.process(files); |
|
| 48 |
@Override |
|
| 49 |
public void process(List<String> orderedTextIDs) {
|
|
| 50 |
super.process(orderedTextIDs); |
|
| 48 | 51 |
|
| 49 |
if (files == null) {
|
|
| 50 |
files = inputDirectory.listFiles(); |
|
| 51 |
if (files != null) Collections.sort(files); |
|
| 52 |
} |
|
| 52 |
if (orderedTextIDs == null) { module.getProject().getTextsID() }
|
|
| 53 | 53 |
|
| 54 | 54 |
if (!doDefaultEditionStep()) return; |
| 55 | 55 |
if (!doFacsEditionStep()) return; |
| 56 |
|
|
| 57 |
// remove extra XSL editions -> they will be recreated by the doPostEditionXSLStep call
|
|
| 56 |
|
|
| 57 |
// remove extra XSL editions -> they will be recreated by the doPostEditionXSLStep call |
|
| 58 | 58 |
for (EditionDefinition eDef : project.getEditionDefinitions()) {
|
| 59 | 59 |
if (eDef.getName() != "facs" && eDef.getName() != "default") {
|
| 60 | 60 |
eDef.delete(); |
| ... | ... | |
| 74 | 74 |
} |
| 75 | 75 |
|
| 76 | 76 |
def second = 0 |
| 77 |
def texts = module.getProject().getTexts() |
|
| 78 |
println "-- Building 'default' edition of ${texts.size()} texts..."
|
|
| 77 | 79 |
|
| 78 |
println "-- Building 'default' edition of ${files.size()} texts..."
|
|
| 79 |
|
|
| 80 | 80 |
def css = ["css/txm.css", "css/${corpusname}.css"] // default CSS inclusion
|
| 81 | 81 |
|
| 82 | 82 |
// scan existing css files that must be declared in each HTML page |
| 83 | 83 |
if (cssDirectory.exists()) {
|
| 84 | 84 |
def cssFiles = cssDirectory.listFiles(); |
| 85 |
if (cssFiles != null) |
|
| 85 |
if (cssFiles != null) {
|
|
| 86 | 86 |
for (File cssFile : cssFiles) {
|
| 87 | 87 |
if (cssFile.isFile() && !cssFile.isHidden() && cssFile.getName().endsWith(".css"))
|
| 88 | 88 |
css << "css/"+cssFile.getName(); |
| 89 | 89 |
} |
| 90 |
} |
|
| 90 | 91 |
} |
| 91 | 92 |
|
| 92 |
ConsoleProgressBar cpb = new ConsoleProgressBar(files.size()) |
|
| 93 |
for (File txmFile : files) {
|
|
| 93 |
ConsoleProgressBar cpb = new ConsoleProgressBar(texts.size()) |
|
| 94 |
for (Text text : texts) {
|
|
| 95 |
|
|
| 96 |
File txmFile = text.getXMLTXMFile() |
|
| 94 | 97 |
try {
|
| 95 | 98 |
cpb.tick() |
| 96 |
String textname = txmFile.getName(); |
|
| 97 |
int i = textname.lastIndexOf(".");
|
|
| 98 |
if (i > 0) textname = textname.substring(0, i); |
|
| 99 | 99 |
|
| 100 |
String textname = text.getName() |
|
| 101 |
|
|
| 100 | 102 |
File firstHTMLPageFile = new File(outputDirectory, textname+"_1.html"); |
| 101 |
if (firstHTMLPageFile.exists() && firstHTMLPageFile.lastModified() >= txmFile.lastModified()) continue; |
|
| 103 |
boolean mustBuild = false; |
|
| 104 |
if (!firstHTMLPageFile.exists() || txmFile.lastModified() >= firstHTMLPageFile.lastModified()) {
|
|
| 105 |
mustBuild = true |
|
| 106 |
} |
|
| 107 |
|
|
| 108 |
if (!text.isDirty() && !mustBuild) {
|
|
| 109 |
Log.finer("skipping 'default html' step of $text");
|
|
| 110 |
continue |
|
| 111 |
} |
|
| 102 | 112 |
|
| 113 |
Edition edition = text.getEdition("default")
|
|
| 114 |
if (edition != null) {
|
|
| 115 |
edition.delete() |
|
| 116 |
} |
|
| 117 |
|
|
| 118 |
edition = new Edition(text); |
|
| 119 |
|
|
| 103 | 120 |
List<String> NoSpaceBefore = LangFormater.getNoSpaceBefore(lang); |
| 104 | 121 |
List<String> NoSpaceAfter = LangFormater.getNoSpaceAfter(lang); |
| 105 | 122 |
|
| 106 |
Text t = project.getText(textname); |
|
| 107 |
if (t == null) {
|
|
| 108 |
t = new Text(project); |
|
| 109 |
} |
|
| 110 |
t.setName(textname); |
|
| 111 |
t.setSourceFile(txmFile) |
|
| 112 |
t.setTXMFile(txmFile) |
|
| 113 | 123 |
|
| 114 | 124 |
def ed = new XTZDefaultPagerStep(this, txmFile, textname, NoSpaceBefore, NoSpaceAfter, css); |
| 115 | 125 |
if (!ed.process()) {
|
| 116 | 126 |
println "Fail to build 'default' edition for text: $txmFile" |
| 117 | 127 |
continue; |
| 118 | 128 |
} |
| 119 |
Edition edition = t.getEdition("default")
|
|
| 120 |
if (edition == null) {
|
|
| 121 |
edition = new Edition(t); |
|
| 122 |
} |
|
| 129 |
|
|
| 123 | 130 |
edition.setName("default");
|
| 124 | 131 |
edition.setIndex(outputDirectory.getAbsolutePath()); |
| 125 |
|
|
| 126 |
for (i = 0 ; i < ed.getPageFiles().size();) {
|
|
| 132 |
|
|
| 133 |
for (int i = 0 ; i < ed.getPageFiles().size();) {
|
|
| 127 | 134 |
File f = ed.getPageFiles().get(i); |
| 128 | 135 |
String wordid = "w_0"; |
| 129 | 136 |
if (i < ed.getIdx().size()) wordid = ed.getIdx().get(i); |
| ... | ... | |
| 165 | 172 |
|
| 166 | 173 |
String imageDirectoryPath = project.getEditionDefinition("facs").getImagesDirectory();
|
| 167 | 174 |
File imageDirectory = null |
| 168 |
|
|
| 175 |
|
|
| 169 | 176 |
if (imageDirectoryPath != null) {
|
| 170 | 177 |
imageDirectoryPath = imageDirectoryPath.trim() |
| 171 | 178 |
imageDirectory = new File(imageDirectoryPath) |
| ... | ... | |
| 176 | 183 |
|
| 177 | 184 |
def second = 0 |
| 178 | 185 |
|
| 179 |
println "-- Building 'facs' edition of ${files.size()} texts..."
|
|
| 186 |
def texts = module.getProject().getTexts() |
|
| 187 |
println "-- Building 'facs' edition of ${texts.size()} texts..."
|
|
| 180 | 188 |
File newEditionDirectory = new File(htmlDirectory, "facs"); |
| 181 | 189 |
newEditionDirectory.mkdir(); |
| 182 | 190 |
|
| 183 |
ConsoleProgressBar cpb = new ConsoleProgressBar(files.size())
|
|
| 184 |
for (File txmFile : files) {
|
|
| 191 |
ConsoleProgressBar cpb = new ConsoleProgressBar(texts.size())
|
|
| 192 |
for (Text text : texts) {
|
|
| 185 | 193 |
cpb.tick() |
| 186 |
String txtname = txmFile.getName(); |
|
| 187 |
int i = txtname.lastIndexOf(".");
|
|
| 188 |
if (i > 0) txtname = txtname.substring(0, i); |
|
| 189 | 194 |
|
| 195 |
File txmFile = text.getXMLTXMFile() |
|
| 196 |
String txtname = text.getName() |
|
| 197 |
|
|
| 190 | 198 |
File firstHTMLPageFile = new File(newEditionDirectory, txtname+"_1.html"); |
| 191 |
if (firstHTMLPageFile.exists() && firstHTMLPageFile.lastModified() >= txmFile.lastModified()) continue; |
|
| 199 |
boolean mustBuild = false; |
|
| 200 |
if (!firstHTMLPageFile.exists() || txmFile.lastModified() >= firstHTMLPageFile.lastModified()) {
|
|
| 201 |
mustBuild = true |
|
| 202 |
} |
|
| 203 |
|
|
| 204 |
if (!text.isDirty() && !mustBuild) {
|
|
| 205 |
Log.finer("skipping 'default html' step of $text");
|
|
| 206 |
continue |
|
| 207 |
} |
|
| 192 | 208 |
|
| 209 |
Edition edition = text.getEdition("facs")
|
|
| 210 |
if (edition != null) {
|
|
| 211 |
edition.delete() |
|
| 212 |
} |
|
| 213 |
|
|
| 214 |
edition = new Edition(text); |
|
| 215 |
|
|
| 193 | 216 |
List<String> NoSpaceBefore = LangFormater.getNoSpaceBefore(lang); |
| 194 | 217 |
List<String> NoSpaceAfter = LangFormater.getNoSpaceAfter(lang); |
| 195 | 218 |
|
| 196 |
Text t = project.getText(txtname); |
|
| 197 |
if (t == null) {
|
|
| 198 |
t = new Text(project); |
|
| 199 |
} |
|
| 200 |
t.setName(txtname); |
|
| 201 |
t.setSourceFile(txmFile) |
|
| 202 |
t.setTXMFile(txmFile) |
|
| 203 |
|
|
| 204 |
Edition edition = t.getEdition("facs")
|
|
| 205 |
if (edition == null) {
|
|
| 206 |
edition = new Edition(t); |
|
| 207 |
} |
|
| 208 | 219 |
edition.setName("facs");
|
| 209 | 220 |
edition.setIndex(outputDirectory.getAbsolutePath()); |
| 210 | 221 |
|
| ... | ... | |
| 216 | 227 |
} |
| 217 | 228 |
|
| 218 | 229 |
def pages = ed.getPageFiles() |
| 219 |
for (i = 0 ; i < pages.size();) {
|
|
| 230 |
for (int i = 0 ; i < pages.size();) {
|
|
| 220 | 231 |
File f = pages[i][0]; |
| 221 | 232 |
String wordid = pages[i][1] |
| 222 | 233 |
//TODO replace '""+(++i)' with something that fetch/findout the page 'name' |
| ... | ... | |
| 231 | 242 |
} |
| 232 | 243 |
} |
| 233 | 244 |
|
| 234 |
|
|
| 245 |
|
|
| 235 | 246 |
if (!imageDirectoryPath.startsWith("http") && imageDirectory != null) { // copy files only if local
|
| 236 | 247 |
File editionImagesDirectory = new File(newEditionDirectory, "res/images/"+corpusname+"/facs"); |
| 237 | 248 |
editionImagesDirectory.mkdirs(); |
| ... | ... | |
| 281 | 292 |
String s = project.getEditionDefinition("default").getWordsPerPage();
|
| 282 | 293 |
if (s != null && s.length() > 0) |
| 283 | 294 |
|
| 284 |
// shared XSL parameters |
|
| 295 |
// shared XSL parameters
|
|
| 285 | 296 |
xslParams["number-words-per-page"] = Integer.parseInt(s); |
| 286 | 297 |
xslParams["pagination-element"] = project.getEditionDefinition("default").getPageElement();
|
| 287 | 298 |
xslParams["import-xml-path"] = project.getProjectDirectory() |
| 288 | 299 |
//println "XSL PARAMS: "+xslParams |
| 289 | 300 |
|
| 290 | 301 |
def xslFiles = xslDirectory.listFiles() |
| 291 |
xslFiles = xslFiles.sort() { f ->
|
|
| 302 |
xslFiles = xslFiles.sort() { f ->
|
|
| 292 | 303 |
try {
|
| 293 |
return Integer.parseInt(f.getName().substring(0, f.getName().indexOf("-")))
|
|
| 304 |
return Integer.parseInt(f.getName().substring(0, f.getName().indexOf("-")))
|
|
| 294 | 305 |
} catch(Exception e) {}
|
| 295 | 306 |
return -1; |
| 296 | 307 |
} |
| ... | ... | |
| 323 | 334 |
|
| 324 | 335 |
if (editionsCreated[editionName] == null) { // first XSL, replace an edition
|
| 325 | 336 |
editionsCreated[editionName] = xslFile |
| 326 |
//if (!importModule.isUpdatingCorpus()) {
|
|
| 327 |
//TODO: optimisation if update is enable, |
|
| 337 |
|
|
| 328 | 338 |
newEditionDirectory.deleteDir(); // delete previous edition if any |
| 329 |
//} |
|
| 330 | 339 |
newEditionDirectory.mkdir() |
| 331 | 340 |
|
| 332 | 341 |
boolean deleteOutputFiles = "pager" == pagerStep; |
| 342 |
|
|
| 333 | 343 |
if (ApplyXsl2.processImportSources(xslFile, inputDirectory, newEditionDirectory, xslParams, deleteOutputFiles)) {
|
| 334 | 344 |
println "" |
| 335 | 345 |
} else {
|
| ... | ... | |
| 384 | 394 |
|
| 385 | 395 |
getFirstWordIDs(textName, editionName, newEditionDirectory, xslFile, txmFile); |
| 386 | 396 |
} |
| 387 |
|
|
| 397 |
|
|
| 388 | 398 |
def editionDeclaration = project.getEditionDefinition(editionName); // create the edition definition |
| 389 | 399 |
editionDeclaration.setBuildEdition(true) |
| 390 | 400 |
editionDeclaration.setPageBreakTag(project.getEditionDefinition("default").getPageElement())
|
| tmp/org.txm.groovy.core/src/groovy/org/txm/scripts/importer/xtz/XTZDefaultPagerStep.groovy (revision 2246) | ||
|---|---|---|
| 211 | 211 |
pagedWriter = new StaxStackWriter(outfile, "UTF-8"); |
| 212 | 212 |
|
| 213 | 213 |
//pagedWriter.writeStartDocument() |
| 214 |
pagedWriter.writeDTD("<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.0 Transitional//EN\" \"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">")
|
|
| 214 |
pagedWriter.writeDTD("<!DOCTYPE html>")
|
|
| 215 | 215 |
pagedWriter.writeCharacters("\n")
|
| 216 | 216 |
pagedWriter.writeStartElement("html");
|
| 217 | 217 |
pagedWriter.writeCharacters("\n")
|
| tmp/org.txm.groovy.core/src/groovy/org/txm/scripts/importer/xtz/XTZImporter.groovy (revision 2246) | ||
|---|---|---|
| 115 | 115 |
Toolbox.getPreference(TBXPreferences.METADATA_TXTSEPARATOR), 1) |
| 116 | 116 |
} |
| 117 | 117 |
|
| 118 |
String cleanDirectories = project.getCleanAfterBuild(); |
|
| 118 |
// remove previous Text if any |
|
| 119 |
project.deleteChildren(Text.class); |
|
| 120 |
|
|
| 121 |
|
|
| 122 |
// main workflow of XTZ importer step |
|
| 123 |
|
|
| 119 | 124 |
|
| 120 | 125 |
if (!doFixSurrogates()) return; |
| 121 | 126 |
if (!doSplitMergeXSLStep()) return; |
| ... | ... | |
| 126 | 131 |
if (!doEncodeMileStonesStep()) return; |
| 127 | 132 |
if (!doToXMLTXMStep()) return; |
| 128 | 133 |
if (!doInjectMetadataStep()) return; |
| 129 |
|
|
| 134 |
|
|
| 130 | 135 |
isSuccessFul = filesToProcess.size() > 0 |
| 131 | 136 |
|
| 137 |
String cleanDirectories = project.getCleanAfterBuild(); |
|
| 132 | 138 |
if ("true".equals(cleanDirectories)) {
|
| 133 | 139 |
new File(module.getBinaryDirectory(), "tokenized").deleteDir() |
| 134 | 140 |
new File(module.getBinaryDirectory(), "src").deleteDir() |
| tmp/org.txm.groovy.core/src/groovy/org/txm/scripts/importer/xml/pager.groovy (revision 2246) | ||
|---|---|---|
| 209 | 209 |
pagedWriter = new StaxStackWriter(outfile, "UTF-8"); |
| 210 | 210 |
|
| 211 | 211 |
//pagedWriter.writeStartDocument() |
| 212 |
pagedWriter.writeDTD("<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.0 Transitional//EN\" \"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">")
|
|
| 212 |
pagedWriter.writeDTD("<!DOCTYPE html>")
|
|
| 213 | 213 |
pagedWriter.writeCharacters("\n")
|
| 214 | 214 |
pagedWriter.writeStartElement("html");
|
| 215 | 215 |
pagedWriter.writeCharacters("\n")
|
| tmp/org.txm.groovy.core/src/groovy/org/txm/scripts/importer/tmx/pager.groovy (revision 2246) | ||
|---|---|---|
| 182 | 182 |
multiwriter = new OutputStreamWriter(new FileOutputStream(outfile) , "UTF-8"); |
| 183 | 183 |
|
| 184 | 184 |
multiwriter.write("<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n");
|
| 185 |
multiwriter.write("<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.0 Transitional//EN\" \"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">\n")
|
|
| 185 |
multiwriter.write("<!DOCTYPE html>\n")
|
|
| 186 | 186 |
multiwriter.write("<html>");
|
| 187 | 187 |
multiwriter.write("<head>");
|
| 188 | 188 |
multiwriter.write("<title>"+basename.toUpperCase()+" $txtname Edition - Page "+pagecount+"</title>");
|
| tmp/org.txm.groovy.core/src/groovy/org/txm/scripts/importer/transcriber/importer.groovy (revision 2246) | ||
|---|---|---|
| 133 | 133 |
if (metadatas != null) {
|
| 134 | 134 |
if (metadatas.getHeadersList().size() > 0) {
|
| 135 | 135 |
|
| 136 |
println "Injecting metadatas "+metadatas.getHeadersList()+" in "+trsfiles.size()+" files"
|
|
| 136 |
println "Injecting metadata "+metadatas.getHeadersList()+" in "+trsfiles.size()+" files" |
|
| 137 | 137 |
|
| 138 | 138 |
trsfiles = txmDir.listFiles(); |
| 139 | 139 |
trsfiles.sort() |
| ... | ... | |
| 142 | 142 |
if (metadatas != null && metadatas.isInitialized()) {
|
| 143 | 143 |
print "." |
| 144 | 144 |
if (!metadatas.injectMetadatasInXml(infile, outfile, "text")) {
|
| 145 |
println("Failed to inject metadatas in "+infile)
|
|
| 145 |
println("Failed to inject metadata in "+infile)
|
|
| 146 | 146 |
outfile.delete() |
| 147 | 147 |
} |
| 148 | 148 |
if (!infile.delete()) {
|
| tmp/org.txm.groovy.core/src/groovy/org/txm/scripts/importer/transcriber/transcriberLoader.groovy (revision 2246) | ||
|---|---|---|
| 101 | 101 |
//get metadata values from CSV |
| 102 | 102 |
Metadatas metadatas; // text metadata |
| 103 | 103 |
File allMetadataFile = Metadatas.findMetadataFile(srcDir); |
| 104 |
println "Trying to read metadatas values from: "+allMetadataFile
|
|
| 104 |
println "Trying to read metadata values from: "+allMetadataFile |
|
| 105 | 105 |
if (allMetadataFile.exists()) {
|
| 106 | 106 |
File copy = new File(binDir, allMetadataFile.getName()) |
| 107 | 107 |
if (!FileCopy.copy(allMetadataFile, copy)) {
|
Formats disponibles : Unified diff