root / tmp / org.txm.core / src / java / org / txm / scripts / importer / HTML2XHTML.groovy @ 1688
History | View | Annotate | Download (1.2 kB)
| 1 |
package org.txm.scripts.importer
|
|---|---|
| 2 |
|
| 3 |
import org.txm.utils.CharsetDetector; |
| 4 |
import org.txm.importer.ValidateXml; |
| 5 |
|
| 6 |
File infile = new File("/home/mdecorde/Bureau/matrice/témoignages/CONVERSIONS/jod/odt.html") |
| 7 |
File outfile = new File("/home/mdecorde/Bureau/matrice/témoignages/CONVERSIONS/jod/odt.xml") |
| 8 |
|
| 9 |
String encoding = new CharsetDetector(infile).getEncoding(); |
| 10 |
println "Encoding: $encoding"
|
| 11 |
String text = infile.getText(encoding);
|
| 12 |
|
| 13 |
//lower case tags
|
| 14 |
text = text.replaceAll(/(<[^!][^>]*>)/,
|
| 15 |
{ full, word ->
|
| 16 |
//fix attributes TRUC=sdf234
|
| 17 |
word = word.replaceAll("([A-Z]+=)([^\" >]+)([ >])",'$1"$2"$3' ) |
| 18 |
word.toLowerCase() // bourrin
|
| 19 |
} ) |
| 20 |
|
| 21 |
//lower case <.> tags
|
| 22 |
text = text.replaceAll(/(<.>)/,
|
| 23 |
{ full, word ->
|
| 24 |
word.toLowerCase() |
| 25 |
} ) |
| 26 |
|
| 27 |
//resolve entities
|
| 28 |
text = text.replaceAll(/ /," ") |
| 29 |
|
| 30 |
//close tags
|
| 31 |
text = text.replaceAll(/<br>/,"<br/>") |
| 32 |
text = text.replaceAll(/<meta([^>]*)>/,'<meta$1/>') |
| 33 |
text = text.replaceAll(/<img([^>]*)>/,'<img$1/>') |
| 34 |
|
| 35 |
//remove doctype declaration
|
| 36 |
text = text.replace('<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">', '') |
| 37 |
|
| 38 |
//write&Validate
|
| 39 |
outfile.withWriter(encoding) { writer -> writer.write(text) }
|
| 40 |
if (!ValidateXml.test(outfile)) {
|
| 41 |
println "FILE: $outfile"
|
| 42 |
} |