root / tmp / org.txm.groovy.core / src / groovy / org / txm / scripts / importer / xtz / XTZCompilerStep.groovy @ 2126
History | View | Annotate | Download (7.3 kB)
| 1 |
package org.txm.scripts.importer.xtz;
|
|---|---|
| 2 |
|
| 3 |
import java.io.File; |
| 4 |
import javax.xml.stream.* |
| 5 |
import java.net.URL |
| 6 |
import java.util.HashMap; |
| 7 |
import org.txm.utils.* |
| 8 |
import org.txm.utils.io.* |
| 9 |
import org.txm.importer.xtz.* |
| 10 |
|
| 11 |
/**
|
| 12 |
* Compiles the CQP file of ONE text
|
| 13 |
*
|
| 14 |
* @author mdecorde
|
| 15 |
*
|
| 16 |
*/
|
| 17 |
public class XTZCompilerStep extends Step { |
| 18 |
|
| 19 |
static String FORM = "form"; |
| 20 |
static String ANA = "ana"; |
| 21 |
static String ID = "id"; |
| 22 |
static String TYPE = "type"; |
| 23 |
static String TAB = "\t"; |
| 24 |
static String QUOTE = "\""; |
| 25 |
|
| 26 |
File xmlFile
|
| 27 |
File cqpFile
|
| 28 |
String textname, corpusname, projectname;
|
| 29 |
boolean normalizeAttributeValues = false; |
| 30 |
boolean normalizeAnaValues = true; |
| 31 |
boolean normalizeFormValues = true; |
| 32 |
|
| 33 |
def inputData;
|
| 34 |
XMLInputFactory factory; |
| 35 |
XMLStreamReader parser; |
| 36 |
OutputStreamWriter output;
|
| 37 |
|
| 38 |
def anavalues = [:];
|
| 39 |
def anatypes;
|
| 40 |
|
| 41 |
String WTAG = "w" |
| 42 |
|
| 43 |
public void setNormalizeAttributeValues(boolean n) { |
| 44 |
this.normalizeAttributeValues = n;
|
| 45 |
} |
| 46 |
|
| 47 |
public void setNormalizeAnaValues(boolean n) { |
| 48 |
this.normalizeAnaValues = n;
|
| 49 |
} |
| 50 |
|
| 51 |
public void setNormalizeFormValues(boolean n) { |
| 52 |
this.normalizeFormValues = n;
|
| 53 |
} |
| 54 |
|
| 55 |
public XTZCompilerStep(File xmlFile, File cqpFile, String textname, String corpusname, String projectname, def anatypes, def wtag) { |
| 56 |
this.xmlFile = xmlFile;
|
| 57 |
this.cqpFile = cqpFile;
|
| 58 |
this.textname = textname
|
| 59 |
this.corpusname = corpusname;
|
| 60 |
this.projectname = projectname;
|
| 61 |
this.anatypes = anatypes;
|
| 62 |
this.WTAG = wtag
|
| 63 |
|
| 64 |
try {
|
| 65 |
inputData = xmlFile.toURI().toURL().openStream(); |
| 66 |
factory = XMLInputFactory.newInstance(); |
| 67 |
parser = factory.createXMLStreamReader(inputData); |
| 68 |
|
| 69 |
} catch (Exception ex) { |
| 70 |
System.err.println("Exception while parsing $xmlFile : "+ex); |
| 71 |
} |
| 72 |
} |
| 73 |
|
| 74 |
/**
|
| 75 |
* Creates the output.
|
| 76 |
*
|
| 77 |
* @param dirPathName the dir path name
|
| 78 |
* @param fileName the file name
|
| 79 |
* @return true, if successful
|
| 80 |
*/
|
| 81 |
private boolean createOutput(File f) { |
| 82 |
try {
|
| 83 |
output = new OutputStreamWriter(new BufferedOutputStream(new FileOutputStream(f)) , "UTF-8"); |
| 84 |
return true; |
| 85 |
} catch (Exception e) { |
| 86 |
System.err.println(e);
|
| 87 |
return false; |
| 88 |
} |
| 89 |
} |
| 90 |
|
| 91 |
/**
|
| 92 |
* Transfom file cqp.
|
| 93 |
*
|
| 94 |
* @param dirPathName the dir path name
|
| 95 |
* @param fileName the file name
|
| 96 |
* @return true, if successful
|
| 97 |
*/
|
| 98 |
public boolean process() |
| 99 |
{
|
| 100 |
if (!createOutput(cqpFile))
|
| 101 |
return false; |
| 102 |
|
| 103 |
String headvalue="" |
| 104 |
String vAna = ""; |
| 105 |
String vForm = ""; |
| 106 |
String wordid= ""; |
| 107 |
String vHead = ""; |
| 108 |
|
| 109 |
|
| 110 |
int p_id = 0; |
| 111 |
int s_id = 0; |
| 112 |
|
| 113 |
def divs = [] |
| 114 |
def ncounts = [:] // contains the n values per tags with no attribute |
| 115 |
|
| 116 |
boolean captureword = false; |
| 117 |
boolean flagWord = false; |
| 118 |
boolean flagForm = false; |
| 119 |
boolean flagAna = false; |
| 120 |
|
| 121 |
String anatype = ""; |
| 122 |
String anavalue = ""; |
| 123 |
boolean stopAtFirstSort = true; |
| 124 |
boolean foundtei = false; |
| 125 |
boolean foundtext = false; |
| 126 |
int nWords = 0; |
| 127 |
try {
|
| 128 |
String localname;
|
| 129 |
for (int event = parser.next(); event != XMLStreamConstants.END_DOCUMENT; event = parser.next()) |
| 130 |
{
|
| 131 |
switch (event) {
|
| 132 |
case XMLStreamConstants.START_ELEMENT:
|
| 133 |
localname = parser.getLocalName().toLowerCase(); |
| 134 |
if ("tei".equals(localname)) foundtei = true; |
| 135 |
switch (localname) {
|
| 136 |
case "text": |
| 137 |
foundtext = true;
|
| 138 |
output.write("<text id=\""+textname+"\" base=\""+corpusname+QUOTE + " project=\""+projectname+QUOTE); |
| 139 |
for (int i = 0 ; i < parser.getAttributeCount() ; i++) { |
| 140 |
String attrname = parser.getAttributeLocalName(i);
|
| 141 |
String attrvalue = parser.getAttributeValue(i)
|
| 142 |
|
| 143 |
if (normalizeAttributeValues)
|
| 144 |
attrvalue = attrvalue.trim(); |
| 145 |
|
| 146 |
if (attrname != ID)
|
| 147 |
output.write(" "+attrname.toLowerCase()+"=\""+attrvalue+QUOTE) |
| 148 |
} |
| 149 |
output.write(">\n");
|
| 150 |
|
| 151 |
break;
|
| 152 |
|
| 153 |
case WTAG: |
| 154 |
for (int i = 0 ; i < parser.getAttributeCount(); i++) { |
| 155 |
if (parser.getAttributeLocalName(i).equals(ID)) {
|
| 156 |
wordid = parser.getAttributeValue(i); |
| 157 |
} |
| 158 |
} |
| 159 |
anavalues = [:]; |
| 160 |
flagWord = true
|
| 161 |
nWords++ |
| 162 |
break;
|
| 163 |
case FORM: |
| 164 |
flagForm = true;
|
| 165 |
vForm = "";
|
| 166 |
vAna = "";
|
| 167 |
break;
|
| 168 |
|
| 169 |
case ANA: |
| 170 |
flagAna = true;
|
| 171 |
anavalue = "";
|
| 172 |
for (int i = 0 ; i < parser.getAttributeCount(); i++) { |
| 173 |
//println parser.getAttributeLocalName(i)+"="+parser.getAttributeValue(i)
|
| 174 |
if (TYPE.equals(parser.getAttributeLocalName(i))) {
|
| 175 |
anatype = parser.getAttributeValue(i).substring(1);//remove the # |
| 176 |
break;
|
| 177 |
} |
| 178 |
} |
| 179 |
break;
|
| 180 |
|
| 181 |
default:
|
| 182 |
if (!foundtei || !foundtext) break; |
| 183 |
|
| 184 |
output.write("<"+localname);
|
| 185 |
|
| 186 |
for (int i = 0 ; i < parser.getAttributeCount() ; i++) { |
| 187 |
String attrname = parser.getAttributeLocalName(i);
|
| 188 |
|
| 189 |
String attrvalue = parser.getAttributeValue(i)
|
| 190 |
if (normalizeAttributeValues)
|
| 191 |
attrvalue = attrvalue.trim(); |
| 192 |
|
| 193 |
output.write(" "+attrname.toLowerCase()+"=\""+attrvalue+QUOTE) |
| 194 |
} |
| 195 |
if (parser.getAttributeCount() == 0) { // add the n attribute |
| 196 |
if (!ncounts.containsKey(localname)) ncounts.put(localname, 0); |
| 197 |
int ncount = ncounts.get(localname);
|
| 198 |
ncounts.put(localname, ncount+1);
|
| 199 |
output.write(" n=\""+ncount+QUOTE)
|
| 200 |
} |
| 201 |
output.write(">\n");
|
| 202 |
} |
| 203 |
break;
|
| 204 |
|
| 205 |
case XMLStreamConstants.END_ELEMENT:
|
| 206 |
localname = parser.getLocalName().toLowerCase(); |
| 207 |
switch (localname) {
|
| 208 |
case WTAG: |
| 209 |
for (String type : anatypes) { |
| 210 |
def v = anavalues.get(type);
|
| 211 |
if (v != null) vAna +=TAB+v; |
| 212 |
else vAna +=TAB;
|
| 213 |
} |
| 214 |
vForm = vForm.replaceAll("\n", "").replaceAll("&", "&").replaceAll("<", "<"); |
| 215 |
if (vAna != null) { |
| 216 |
output.write(vForm+TAB+wordid+vAna+"\n");
|
| 217 |
} |
| 218 |
vAna = "";
|
| 219 |
vForm = "";
|
| 220 |
flagWord = false;
|
| 221 |
break;
|
| 222 |
|
| 223 |
case "tei": |
| 224 |
foundtei = false;
|
| 225 |
break;
|
| 226 |
case "text": |
| 227 |
output.write("</text>\n");
|
| 228 |
foundtext = false;
|
| 229 |
break;
|
| 230 |
case FORM: |
| 231 |
flagForm = false;
|
| 232 |
break;
|
| 233 |
case ANA: |
| 234 |
anavalues.put(anatype, anavalue) |
| 235 |
flagAna = false;
|
| 236 |
break;
|
| 237 |
default:
|
| 238 |
if (!foundtei || !foundtext) break; |
| 239 |
|
| 240 |
output.write("</"+localname+">\n"); |
| 241 |
} |
| 242 |
break;
|
| 243 |
|
| 244 |
case XMLStreamConstants.CHARACTERS:
|
| 245 |
if (!foundtei || !foundtext) break; |
| 246 |
if (flagWord) {
|
| 247 |
if (flagForm) {
|
| 248 |
if (normalizeFormValues) {
|
| 249 |
vForm += parser.getText().trim(); |
| 250 |
} else {
|
| 251 |
vForm += parser.getText(); |
| 252 |
} |
| 253 |
} |
| 254 |
if (flagAna) {
|
| 255 |
if (normalizeAnaValues)
|
| 256 |
anavalue += parser.getText().trim(); |
| 257 |
else
|
| 258 |
anavalue += parser.getText(); |
| 259 |
} |
| 260 |
} |
| 261 |
break;
|
| 262 |
} |
| 263 |
} |
| 264 |
|
| 265 |
output.close(); |
| 266 |
if (parser != null) parser.close(); |
| 267 |
if (inputData != null) inputData.close(); |
| 268 |
} catch (Exception ex) { |
| 269 |
System.out.println("Exception while parsing " + inputData+" of Text "+textname+" : "+ex); |
| 270 |
File errorDir = null |
| 271 |
try {
|
| 272 |
errorDir = new File(cqpFile.getParentFile(), "compiler-error") |
| 273 |
println "Warning: Moving $xmlFile to $errorDir"
|
| 274 |
errorDir.mkdir(); |
| 275 |
FileCopy.copy(xmlFile, new File(errorDir, xmlFile.getName())) |
| 276 |
} catch(Exception eCopy) { |
| 277 |
println "Error while moving "+xmlFile+" to "+errorDir+" : "+eCopy |
| 278 |
} |
| 279 |
if (parser != null) parser.close(); |
| 280 |
if (inputData != null) inputData.close(); |
| 281 |
return false; |
| 282 |
} |
| 283 |
if (nWords == 0) { |
| 284 |
println "** no words written."
|
| 285 |
} |
| 286 |
return nWords > 0; |
| 287 |
} |
| 288 |
} |