Laboratoire ICAR » Plateforme TXM

// Copyright © 2015 - ENS de Lyon - http://textometrie.ens-lyon.fr

// @author sheiden

//

// This file is part of the TXM platform.

//

// The TXM platform is free software: you can redistribute it and/or modify

// it under the terms of the GNU General Public License as published by

// the Free Software Foundation, either version 3 of the License, or

// (at your option) any later version.

//

// The TXM platform is distributed in the hope that it will be useful,

// but WITHOUT ANY WARRANTY; without even the implied warranty of

// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

// GNU General Public License for more details.

//

// You should have received a copy of the GNU General Public License

// along with the TXM platform.  If not, see <http://www.gnu.org/licenses/>.

//

// $LastChangedDate: 2013-05-02 11:28:42 +0200 (jeu., 02 mai 2013) $

// $LastChangedRevision: 2378 $

// $LastChangedBy: sheiden $

//

package org.txm.macro.csv

import org.kohsuke.args4j.*

import groovy.transform.Field

import java.nio.charset.Charset

import org.txm.rcpapplication.swt.widget.parameters.*

import org.txm.utils.*

import org.txm.importer.*

import javax.xml.stream.*

import java.net.URL

//import org.apache.xerces.util

@Field @Option(name="inputFile",usage="CSV File", widget="File", required=false, def="/home/sheiden/Corpus/src/charlie/csv/fr_07jan.csv")

File inputFile;

@Field @Option(name="columnSeparator",usage="column columnSeparator", widget="String", required=false, def=",")

def columnSeparator;

@Field @Option(name="characterEncoding",usage="File characterEncoding", widget="String", required=false, def="UTF-8")

def characterEncoding;

@Field @Option(name="rootTag",usage="Root tag name", widget="String", required=false, def="tweets")

def rootTag;

@Field @Option(name="textTag",usage="Text tag name", widget="String", required=false, def="tweet")

def textTag;

@Field @Option(name="metadataColumnList",usage="metadataColumnList column list separated with comma", widget="String", required=false, def="tweet-id-str,job-id,created-at,from-user,from-user-id-str,from-user-name,from-user-fullname,from-user-followers,from-user-following,from-user-favorites,from-user-tweets,from-user-timezone,to-user,to-user-id-str,to-user-name,source,location-geo,location-geo-0,location-geo-1,iso-language,analysis-state")

def metadataColumnList;

@Field @Option(name="textColumnList",usage="textColumnList column list separated with comma", widget="String", required=false, def="text")

def textColumnList;

if (!ParametersDialog.open(this)) return;

metadataColumnList = metadataColumnList.split(",")

textColumnList = textColumnList.split(",")

textTag = textTag.trim()

rootTag = rootTag.trim()

CsvReader reader = new CsvReader(inputFile.getAbsolutePath(), columnSeparator.charAt(0), Charset.forName(characterEncoding));

if (!reader.readHeaders()) {

	println "Error: no header"

	return

}

def headers = Arrays.asList(reader.getHeaders())

headers.eachWithIndex {str, index -> headers[index] = str.replaceAll(/_/, "-") }

reader.setHeaders(headers as String[])

println "Root tag: $rootTag"

println "Text tag: $textTag"

println "Metadata column(s): $metadataColumnList"

println "Text column(s): $textColumnList"

println "Processing..."

def ok = true

for (String m : metadataColumnList) {

	m = m.trim()

	if (!headers.contains(m)) {

		println "Error: missing metadata column named '$m'"

		ok = false

	}

}

for (String t : textColumnList) {

	t = t.trim()

	if (!headers.contains(t)) {

		println "Error: missing text column named '$t'"

		ok = false

	}

}

if (!ok) {

	println "** CSV2XML: Column(s) missing, aborting..."

	return

}

String name = inputFile.getName()

int idx = name.indexOf(".")

if (idx > 0) name = name.substring(0, idx)

File outputfile = new File(inputFile.getParentFile(), name+".xml")

XMLOutputFactory factory = XMLOutputFactory.newInstance()

Writer output = new OutputStreamWriter(new FileOutputStream(outputfile) , "UTF-8")

XMLStreamWriter writer = factory.createXMLStreamWriter(output)

writer.writeStartDocument("UTF-8", "1.0")

writer.writeCharacters("\n")

writer.writeStartElement(rootTag)

writer.writeCharacters("\n")

int pb_n = 1

def tweet = [:]

def isAllValidXmlChars = { s ->

// xml 1.1 spec http://en.wikipedia.org/wiki/Valid_characters_in_XML

if (!s ==~ /[\u0001-\uD7FF\uE000-\uFFFD\x{10000}-\x{10FFFF}]/) {

  // not in valid ranges

  return false

}

if (s ==~ /[\u0001-\u0008\u000b-\u000c\u000E-\u001F\u007F-\u0084\u0086-\u009F]/) {

  // a control character

  return false

}

// "Characters allowed but discouraged"

if (s ==~ /[\uFDD0-\uFDEF\x{1FFFE}-\x{1FFFF}\x{2FFFE}–\x{2FFFF}\x{3FFFE}–\x{3FFFF}\x{4FFFE}–\x{4FFFF}\x{5FFFE}-\x{5FFFF}\x{6FFFE}-\x{6FFFF}\x{7FFFE}-\x{7FFFF}\x{8FFFE}-\x{8FFFF}\x{9FFFE}-\x{9FFFF}\x{AFFFE}-\x{AFFFF}\x{BFFFE}-\x{BFFFF}\x{CFFFE}-\x{CFFFF}\x{DFFFE}-\x{DFFFF}\x{EFFFE}-\x{EFFFF}\x{FFFFE}-\x{FFFFF}\x{10FFFE}-\x{10FFFF}]/) {

  return false

}

return true

}

def stripInvalidXmlCharacters = { input ->

    StringBuilder sb = new StringBuilder();

    for (int i = 0; i < input.length(); i++) {

        char c = input.charAt(i);

//        if (XMLChar.isValid(c)) {

        if (isAllValidXmlChars(c)) {

            sb.append(c);

        }

    }

    return sb.toString();

}

def tokenizeAs

tokenizeAs = { source, matchers ->

	if (matchers.size() > 0) {

		def inputPattern = matchers[0]

		def outputElement = matchers[1]

		def outputAttribute = matchers[2]

		def outputAttValue = matchers[3]

		matchers = matchers.drop(4)

		def m = (source =~ inputPattern)

		def lastMatch = 0

		while(m.find()) {

		   tokenizeAs(source.substring(lastMatch, m.start()), matchers)

		   if (outputAttribute == "type" && outputAttValue == "url") {

		   		writer.writeStartElement("a")

		   		writer.writeAttribute("href", m.group())

		   }

		   writer.writeStartElement(outputElement)

		   writer.writeAttribute(outputAttribute, outputAttValue)

		   writer.writeAttribute("frpos", "NAM")

		   writer.writeAttribute("frlemma", m.group())

		   writer.writeCharacters(m.group())

		   writer.writeEndElement()

		   if (outputAttribute == "type" && outputAttValue == "url") {

		   		writer.writeEndElement()

		   }

		   lastMatch = m.end()

		}

		tokenizeAs(source.substring(lastMatch), matchers)

	} else {

		writer.writeCharacters(source)

	}

}

while (reader.readRecord()) {

    writer.writeCharacters("  ")

	writer.writeEmptyElement("pb") // <pb/>

	writer.writeAttribute("n", ""+pb_n++)

	writer.writeCharacters("\n")

    writer.writeCharacters("  ")

	writer.writeStartElement(textTag)

	for (String m : metadataColumnList) {

		m = m.trim()

		writer.writeAttribute(m, CleanFile.clean(reader.get(m)))

	}

    writer.writeCharacters("\n")

	for (String t : textColumnList) {

		t = t.trim()

    	writer.writeCharacters("    ")

		writer.writeStartElement(t)

		// look for re-tweets

		def c = reader.get(t)

		def retweet = false

		def rt_pattern = ~/(?s:^RT @[^:]+: (.*)$)/

		def rt_m = (c =~ rt_pattern)

		if (rt_m) retweet = true 

		if (retweet) { // it is a re-tweet

			// take off and count all re-tweet prefixes

			def nPrefix = 0

			while (retweet) {

				c = rt_m.group(1)

				rt_m = (c =~ rt_pattern)

				if (rt_m) { retweet = true } else { retweet = false }

				nPrefix++

			}

			def crt = sprintf("RT-%d ", nPrefix)+c

			def n = tweet.get(crt)

			if (n) {

				tweet.put(crt, n+1)

				} else {

				tweet.put(crt, 1)

			}

		} else {

			tweet.put(c, 1)

			tokenizeAs(CleanFile.clean(c),\

					   [/@\p{L}+/, "w", "type", "attag",\

						/#\p{L}+/, "w", "type", "hashtag",\

						/((http|ftp|https):\/\/[\p{L}\-_]+(\.[\p{L}\-_]+)+([\p{L}\-\.,@?^=%&:\/~\+#]*[\p{L}\-\@?^=%&\/~\+#])?)/, "w", "type", "url"])

		}

		writer.writeEndElement() // t

		writer.writeCharacters("\n")

	}

    writer.writeCharacters("  ")

	writer.writeEndElement() // textTag

	writer.writeCharacters("\n")

}

writer.writeEndElement() // rootTag

writer.writeCharacters("\n")

writer.close()

output.close()

reader.close()

def nt = tweet.size()

println sprintf("\n%d tweets uniques sur %d lus", nt, pb_n-1)

if (nt > 50) {

	nt = 50

	println "Printing first 50 most frequent [re-]tweets:"

}

// take(nt).

tweet.sort { -it.value }.each { entry ->

	def l = entry.key.length()

	if (l > 0) {

//		if (entry.key.find("On n'a pas peur !!")) {

		println sprintf("[%d] %s...", entry.value, entry.key[0..(Math.min(entry.key.length(), 100)-1)])

//		}

	} else {

	println sprintf("Empty tweet content occurring %d times.", entry.value)

	}

}

package org.txm.macro.txt

// Copyright © - ENS de Lyon - http://textometrie.ens-lyon.fr

// @author sheiden

//

// This file is part of the TXM platform.

//

// The TXM platform is free software: you can redistribute it and/or modify

// it under the terms of the GNU General Public License as published by

// the Free Software Foundation, either version 3 of the License, or

// (at your option) any later version.

//

// The TXM platform is distributed in the hope that it will be useful,

// but WITHOUT ANY WARRANTY; without even the implied warranty of

// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

// GNU General Public License for more details.

//

// You should have received a copy of the GNU General Public License

// along with the TXM platform.  If not, see <http://www.gnu.org/licenses/>.

//

// $LastChangedDate: 2013-05-02 11:28:42 +0200 (jeu., 02 mai 2013) $

// $LastChangedRevision: 2378 $

// $LastChangedBy: sheiden $

//

// STANDARD DECLARATIONS

// imports

import org.kohsuke.args4j.*

import groovy.transform.Field

import org.txm.rcpapplication.swt.widget.parameters.*

// PARAMETERS

// **change this parameter**

@Field @Option(name="inputDirectory", usage="Dossier contenant les fichiers à modifier", widget="Folder", required=true, def='/home')

		inputDirectory = new File(System.getProperty("user.home"), "Bureau/voeux")

// **change this parameter**

@Field @Option(name="extension", usage="extension des fichiers à modifier (expression régulière)", widget="String", required=true, def='\\.txt')

		extension = "\\.txt"

// **change this parameter**

@Field @Option(name="find", usage="Expression régulière à chercher", widget="String", required=true, def='’')

		find = "’"

// **change this parameter**

@Field @Option(name="replaceWith", usage="Chaîne de remplacement", widget="String", required=false, def='\'')

		replaceWith = "'"

// **change this parameter**

@Field @Option(name="encoding", usage="Encodage des caractères des fichiers", widget="String", required=true, def='UTF-8')

		encoding = "utf-8"

// PARAMETERS DIALOG

if (!ParametersDialog.open(this)) return;

// SANITY CHECK

if (inputDirectory==null || find==null || replaceWith==null) { println "** MultiLineSearchReplaceInDirectoryMacro: the input directory, the regular expression to search and replacement must be specified."; return}

if (!inputDirectory.exists()) { println "** MultiLineSearchReplaceInDirectoryMacro: impossible to access the '$inputDirectory' input directory."; return}

// MAIN BODY

println "-- working in $inputDirectory directory with files of '$extension' extension"

println "-- replacing '$find' with '$replaceWith'"

// find = /date="([0-9]+)-([0-9]+-[0-9]+)"/

// **change this parameter**

// replaceWith = 'date="$1-$2" year="$1"'

// **change this parameter** (warning: '$1', '$2'... can be interpreted by Groovy in "..." strings)

//

// RECETTE

// <tei:pb [^>]+>\n   <tei:p>[0-9]+</tei:p>\n   <tei:p>[^ ]+ 18[5-6][0-9]\.</tei:p>\n

def p = /$find/

inputDirectory.eachFileMatch(~/.*$extension/) { file ->               // for each file matching extension

	println "\n-- processing: "+file.getName()

	def tmp = File.createTempFile("SearchReplaceInDirectoryTemp", ".tmp", file.getParentFile()) // create temporary file

	tmp.withWriter(encoding) { writer ->

		writer.print(file.getText(encoding).replaceAll(p, replaceWith))

	}

	file.delete()

	tmp.renameTo(file)

}

package org.txm.macro.line

// Copyright © 2018 - ENS de Lyon - http://textometrie.ens-lyon.fr

// @author sheiden

//

// This file is part of the TXM platform.

//

// The TXM platform is free software: you can redistribute it and/or modify

// it under the terms of the GNU General Public License as published by

// the Free Software Foundation, either version 3 of the License, or

// (at your option) any later version.

//

// The TXM platform is distributed in the hope that it will be useful,

// but WITHOUT ANY WARRANTY; without even the implied warranty of

// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

// GNU General Public License for more details.

//

// You should have received a copy of the GNU General Public License

// along with the TXM platform.  If not, see <http://www.gnu.org/licenses/>.

//

// $LastChangedDate: 2013-05-02 11:28:42 +0200 (jeu., 02 mai 2013) $

// $LastChangedRevision: 2378 $

// $LastChangedBy: sheiden $

//

// imports

import org.kohsuke.args4j.*

import groovy.transform.Field

import org.txm.rcpapplication.swt.widget.parameters.*

// parameters

// **change this parameter**

@Field @Option(name="inputFile",usage="fichier Taltac", widget="File", required=true, def='')

def inputFile

// **change this parameter**

@Field @Option(name="characterEncoding",usage="Système d'encodage des caractères utilisé pour le fichier", widget="String", required=true, def='UTF-8')

def characterEncoding = "UTF-8"

@Field @Option(name="titleTag", usage="name of title ++++ tag", widget="String", required=false, def="titolo")

def titleTag

@Field @Option(name="addParagraphs", usage="encode each text line as a paragraph", widget="Boolean", required=true, def="true")

def addParagraphs

if (!ParametersDialog.open(this)) return

name = inputFile.getName()

idx = name.lastIndexOf(".")

if (idx > 0) name = name.substring(0, idx)

outputFile = new File(inputFile.getParentFile(), name+".xml")

pageNum = 2

outputFile.write('') // create empty file

outputFile.withWriter() { writer ->

	writer.println '<?xml version="1.0" encoding="UTF-8"?>\n<taltac>'

	def firstDoc = true

	def inTitle = false

	def currentTag = ""

	def metadata = "<hi>no metadata</hi>"

	def metadataEdited = false

	inputFile.eachLine(characterEncoding) { line ->

		line = line.replaceAll("&", "&")

		line = line.replaceAll("<", "&lt;")

		// ****yahoobanque1 *data=31gen *autore=da *rubrica=da *ora=08 *agenzia=reuters *grafici=da

		group = (line =~ /^\*\*\*\*([^ ]+) (.*)/)

		if (group) {

			ident = group[0][1]

			properties = group[0][2]

			metadata=properties.replaceAll(/ ?\*([^=]+)=([^ ]+)/) { all2, propname, propvalue ->

				"<item><hi>$propname</hi>: $propvalue</item>\n"

			}

			metadata="<list type=\"unordered\">\n"+metadata+"</list>"

			metadataEdited = false

			properties=properties.replaceAll(/\*([^=]+)=([^ ]+)/) { all2, propname, propvalue ->

				"$propname=\"$propvalue\""

			}

			if (firstDoc) {

				firstDoc = false

				writer.println "<doc ident=\"$ident\" $properties>"

			}else{

				if (currentTag.size() > 0) {

					if (titleTag.size() > 0) {

						if (inTitle) {

							writer.println sprintf("</%s>", currentTag)

							writer.println "</head>"

							inTitle = false

							currentTag = ""

						}else{

							writer.println sprintf("</%s>", currentTag)

							currentTag = ""

						}

					}else{

						writer.println sprintf("</%s>", currentTag)

						currentTag = ""

					}

/*

					if (!metadataEdited) {

println sprintf ("ident = %s, currentTag = %s (%d), metadata", ident, currentTag, currentTag.size())

						writer.println metadata

						metadataEdited = true

					}

*/

				}

				writer.println "</doc>\n<pb n=\"${pageNum++}\"/>\n<doc ident=\"$ident\" $properties>"

			}

		}else{

			// ++++titolo

			group = (line =~ /^\+\+\+\+(.+)/)

			if (group) {

				tag = group[0][1]

				if (currentTag.size() > 0) {

					if (titleTag.size() > 0) {

						if (inTitle) {

							writer.println sprintf("</%s>", currentTag)

							writer.println "</head>"

							inTitle = false

							currentTag = ""

						}else{

							writer.println sprintf("</%s>", currentTag)

							currentTag = ""

						}

					}else{

						writer.println sprintf("</%s>", currentTag)

						currentTag = ""

					}

					if (!metadataEdited) {

						writer.println metadata

						metadataEdited = true

					}

				}

				if (titleTag.size() > 0) {

					if (tag == titleTag) {

						writer.println "<head>"

						writer.println sprintf("<%s>", tag)

						inTitle = true

						currentTag = tag

					}else{

						writer.println sprintf("<%s>", tag)

						currentTag = tag

					}

				}else{

					writer.println sprintf("<%s>", tag)

					currentTag = tag

				}

			}else{

				// normal line

				if (addParagraphs) {

					writer.println "<p>$line</p>"

				}else{

					writer.println "$line"

				}

			}

		}

	}

	writer.println sprintf("</%s>\n</doc>\n</taltac>\n", currentTag)

	writer.close()

}

// Copyright © 2015 - ENS de Lyon - http://textometrie.ens-lyon.fr

// @author sheiden

//

// This file is part of the TXM platform.

//

// The TXM platform is free software: you can redistribute it and/or modify

// it under the terms of the GNU General Public License as published by

// the Free Software Foundation, either version 3 of the License, or

// (at your option) any later version.

//

// The TXM platform is distributed in the hope that it will be useful,

// but WITHOUT ANY WARRANTY; without even the implied warranty of

// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

// GNU General Public License for more details.

//

// You should have received a copy of the GNU General Public License

// along with the TXM platform.  If not, see <http://www.gnu.org/licenses/>.

//

// $LastChangedDate: 2013-05-02 11:28:42 +0200 (jeu., 02 mai 2013) $

// $LastChangedRevision: 2378 $

// $LastChangedBy: sheiden $

//

// STANDARD DECLARATIONS

import org.kohsuke.args4j.*

import groovy.transform.Field

import java.nio.charset.Charset

import org.txm.rcpapplication.swt.widget.parameters.*

import org.txm.utils.*

import javax.xml.stream.*

import java.net.URL

import java.util.regex.Matcher;

import java.util.regex.Pattern;

// PARAMETERS

@Field @Option(name="inputDirectory", usage="TXT directory", widget="Folder", required=false, def="")

File inputDirectory;

@Field @Option(name="regexp", usage="Regular expression to match", widget="String", required=false, def="")

String regexp;

@Field @Option(name="encoding", usage="File encoding", widget="String", required=false, def="UTF-8")

String encoding;

// PARAMETERS

if (inputDirectory == null) {

	if (!ParametersDialog.open(this)) return;

}

// SANITY CHECK

if (inputDirectory==null || regexp==null) { println "** FindMultiLineRegExpMacro: the input directory and the regular expression must be specified."; return}

if (!inputDirectory.exists()) { println "** FindMultiLineRegExpMacro: impossible to access the '$inputDirectory' input directory."; return}

// MAIN BODY

def p = /$regexp/

println "-- looking for: $regexp"

for (File inputfile : inputDirectory.listFiles()) {

	if (inputfile.isDirectory()) continue // ignore

	def matcher = inputfile.getText() =~ p

	println "\n-- file:"+inputfile.getName() + " "+matcher.size() + " match" +((matcher.size() > 1)?"s":"")

	if (matcher.size() > 0) {

		matcher.each { println it }

	}

}

package org.txm.macro

import org.kohsuke.args4j.*

import groovy.transform.Field

import java.nio.charset.Charset

import org.txm.rcpapplication.swt.widget.parameters.*

import org.txm.utils.*

import javax.xml.stream.*

import java.net.URL

import java.util.regex.Matcher;

import java.util.regex.Pattern;

@Field @Option(name="inputDirectory",usage="TXT directory", widget="Folder", required=false, def="directory path")

File inputDirectory;

@Field @Option(name="regexp",usage="Regular expression to match", widget="String", required=false, def="regular expression")

String regexp;

@Field @Option(name="encoding",usage="File encoding", widget="String", required=false, def="UTF-8")

String encoding;

if (!ParametersDialog.open(this)) return;

def p = /$regexp/

println "processing: "+inputDirectory.listFiles()

for (File inputfile : inputDirectory.listFiles()) {

	if (inputfile.isDirectory()) continue // ignore

	def lines = []

	inputfile.eachLine("UTF-8") { line, n ->

		def m = line =~ p

		if ( m.size() > 0) {

			lines << "  line $n: $line"

		}

	}

	println inputfile.getName() + " "+lines.size() + " match" +((lines.size() > 1)?"s":"")

	if (lines.size() > 0) {

		for (String s : lines ) println s

	}

}

// STANDARD DECLARATIONS

package org.txm.macro

import org.kohsuke.args4j.*

import groovy.transform.Field

import org.txm.rcpapplication.swt.widget.parameters.*

import ims.tiger.importfilter.*

import ims.tiger.importfilter.bracketing.*

import org.apache.log4j.*

// BEGINNING OF PARAMETERS

// Declare each parameter here

// (available widget types: Query, File, Folder, String, Text, Boolean, Integer, Float and Date)

@Field @Option(name="SourceFile", usage="SourceFilename", widget="File", required=false, def="input.mrg")

def SourceFile

@Field @Option(name="TargetFile", usage="TargetFilename", widget="File", required=false, def="output.xml")

def TargetFile

@Field @Option(name="XMLTargetID", usage="XMLTargetID", widget="String", required=false, def="XMLTargetID")

def XMLTargetID

@Field @Option(name="SourceFolder", usage="SourceFolder (leave empty if SourceFile set)", widget="Folder", required=false, def="input <remove if SourceFile set>")

def SourceFolder

@Field @Option(name="TargetFolder", usage="TargetFolder (leave empty if TargetFile set)", widget="Folder", required=false, def="output")

def TargetFolder

@Field @Option(name="MaximumNumberOfSentences", usage="MaximumNumberOfSentences", widget="Integer", required=true, def="0")

def MaximumNumberOfSentences

// Open the parameters input dialog box

if (!ParametersDialog.open(this)) return

// END OF PARAMETERS

BasicConfigurator.configure()

ImportFilter filter = new MyUPennFilter()

ImportFilterHandler handler = new SilentImportFilterHandler()

filter.setImportFilterHandler(handler)

filter.setCompression(false)

filter.setSchemaFilename(System.getProperty("user.home")+"/TXM/xml/xsd/tiger/TigerXML.xsd")

filter.setMaximumNumberOfSentences(MaximumNumberOfSentences-1)

if (SourceFolder == null) {

	def SourceFilename = SourceFile.getAbsolutePath()

	def TargetFilename = TargetFile.getAbsolutePath()

	filter.setSourceFilename(SourceFilename)

	filter.setXMLTargetFilename(TargetFilename)

	filter.setXMLTargetID(XMLTargetID)

	println "Converting '$SourceFilename' to '$TargetFilename'"

	try {

  			filter.startConversion()

		} catch (Exception e)

		{ e.printStackTrace()

	}

} else {

	for (File inputfile : SourceFolder.listFiles()) {

		if (inputfile.isDirectory()) continue // ignore

		fileNameE = inputfile.getName()

		i = fileNameE.lastIndexOf('.')

		if (i > 0) extension = fileNameE.substring(i+1) else extension = ""

		fileName = fileNameE.substring(0, i)

		fileId = fileName

		input = inputfile.getAbsolutePath()

		output = TargetFolder.getAbsolutePath()+"/"+fileName+".xml"

		println "Converting '"+input+"' to '"+output+"'"

		filter.setSourceFilename(input)

		filter.setXMLTargetFilename(output)

		filter.setXMLTargetID(fileId)

		try {

  				filter.startConversion()

			} catch (Exception e)

			{ e.printStackTrace()

    	}

	}

}

PennTreebank2TIGER macro

========================

2016-07, sheiden

* Install

- unzip PennTreebank2TIGER.zip

- copy TigerXML.xsd in $HOME/TXM/xml/xsd/tiger/TigerXML.xsd

- copy PennTreebank2TIGERMacro.groovy in $HOME/TXM/scripts/macro/org/txm/macro

- refresh macro view

* Parameters

- SourceFile: drives one file conversion process mode

- SourceFolder: drives several files in a folder conversion process mode

-> fill only the field to be used

- TargetFile: if SourceFile then use that target file

- XMLTargetID: if SourceFile then use that target ID

- TargetFolder: : if SourceFolder then use that target folder to save targets

 - target files are named from the source filename with the extension stripped and '.xml' added

 - target ID are named from the source filename with the extension stripped

- MaximumNumberOfSentences: maximum number of sentences to convert per file (set to '0' to convert all sentences)

<?xml version="1.0"?>

<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema">

 <!-- ==================================================================

      XML Schema for the TIGER-XML format

      http://www.ims.uni-stuttgart.de/projekte/TIGER/public/TigerXML.xsd

      ==================================================================

      TIGER Project, Wolfgang Lezius

      IMS, University of Stuttgart, 04/01/2003

      ================================================================== -->

  <!-- ======================================================

       INCLUDES DECLARATION OF THE HEADER

       ====================================================== -->

  <xsd:include schemaLocation="TigerXMLHeader.xsd" />

  <!-- ======================================================

       INCLUDES DECLARATION OF SUBCORPORA AND SENTENCES

       ====================================================== -->

  <xsd:include schemaLocation="TigerXMLSubcorpus.xsd" />

  <!-- ======================================================

       DECLARATION OF THE CORPUS DOCUMENT

       ====================================================== -->

  <!-- declaration of the root element: corpus -->

  <xsd:element name="corpus">

    <xsd:complexType>

      <xsd:sequence>

        <xsd:choice>           

           <!-- header of the document is optional -->

           <xsd:element name="head" type="headType" minOccurs="0" maxOccurs="1"/>

        </xsd:choice>

        <xsd:element name="body" type="bodyType" minOccurs="1" maxOccurs="1"/>

      </xsd:sequence>

      <!-- corpus ID -->

      <xsd:attribute name="id"      type="idType"     use="required" />

      <!-- optional attribute: TigerXML version; used by TIGERSearch only -->

      <xsd:attribute name="version" type="xsd:string" use="optional" />

    </xsd:complexType>

  </xsd:element>

  <!-- declaration of the body type -->

  <xsd:complexType name="bodyType">

    <xsd:choice minOccurs="1" maxOccurs="unbounded">

      <xsd:element name="subcorpus" type="subcorpusType" minOccurs="1" maxOccurs="1"/>

      <xsd:element name="s" type="sentenceType" minOccurs="1" maxOccurs="1"/>

    </xsd:choice>

  </xsd:complexType>

</xsd:schema>