Updated documentation and translations.
This commit is contained in:
parent
5fcab958aa
commit
07b4161051
|
@ -1,28 +0,0 @@
|
||||||
<?xml version="1.0" encoding="UTF-8"?>
|
|
||||||
<module org.jetbrains.idea.maven.project.MavenProjectsManager.isMavenModule="true" type="JAVA_MODULE" version="4">
|
|
||||||
<component name="NewModuleRootManager" LANGUAGE_LEVEL="JDK_1_8">
|
|
||||||
<output url="file://$MODULE_DIR$/target/classes" />
|
|
||||||
<output-test url="file://$MODULE_DIR$/target/test-classes" />
|
|
||||||
<content url="file://$MODULE_DIR$">
|
|
||||||
<sourceFolder url="file://$MODULE_DIR$/src/main/java" isTestSource="false" />
|
|
||||||
<sourceFolder url="file://$MODULE_DIR$/src/main/resources" type="java-resource" />
|
|
||||||
<sourceFolder url="file://$MODULE_DIR$/src/test/java" isTestSource="true" />
|
|
||||||
<excludeFolder url="file://$MODULE_DIR$/target" />
|
|
||||||
</content>
|
|
||||||
<orderEntry type="inheritedJdk" />
|
|
||||||
<orderEntry type="sourceFolder" forTests="false" />
|
|
||||||
<orderEntry type="library" name="Maven: commons-io:commons-io:2.5" level="project" />
|
|
||||||
<orderEntry type="library" name="Maven: org.apache.commons:commons-lang3:3.6" level="project" />
|
|
||||||
<orderEntry type="library" name="Maven: com.googlecode.json-simple:json-simple:1.1.1" level="project" />
|
|
||||||
<orderEntry type="library" name="Maven: junit:junit:4.10" level="project" />
|
|
||||||
<orderEntry type="library" name="Maven: org.hamcrest:hamcrest-core:1.1" level="project" />
|
|
||||||
<orderEntry type="library" name="Maven: org.apache.commons:commons-csv:1.4" level="project" />
|
|
||||||
<orderEntry type="library" name="Maven: org.controlsfx:controlsfx:8.40.13" level="project" />
|
|
||||||
<orderEntry type="library" name="Maven: org.rocksdb:rocksdbjni:5.7.3" level="project" />
|
|
||||||
<orderEntry type="library" name="Maven: org.apache.logging.log4j:log4j-api:2.9.0" level="project" />
|
|
||||||
<orderEntry type="library" name="Maven: org.apache.logging.log4j:log4j-core:2.9.0" level="project" />
|
|
||||||
<orderEntry type="library" name="Maven: org.kordamp.ikonli:ikonli-fontawesome-pack:1.9.0" level="project" />
|
|
||||||
<orderEntry type="library" name="Maven: org.kordamp.ikonli:ikonli-core:1.9.0" level="project" />
|
|
||||||
<orderEntry type="library" name="Maven: org.kordamp.ikonli:ikonli-javafx:1.9.0" level="project" />
|
|
||||||
</component>
|
|
||||||
</module>
|
|
Binary file not shown.
|
@ -11,14 +11,14 @@ The easier option is to download list.zip, extract it and run list.exe.
|
||||||
|
|
||||||
### Run list.jar
|
### Run list.jar
|
||||||
To do this you first need to install the correct version of java (JDK). The program was developed and tested on [JDK Development Kit 21.0.2](https://www.oracle.com/java/technologies/downloads/#java21).
|
To do this you first need to install the correct version of java (JDK). The program was developed and tested on [JDK Development Kit 21.0.2](https://www.oracle.com/java/technologies/downloads/#java21).
|
||||||
If you already have another version of Java installed you might have to delete previous version before you install this version.
|
If you already have another version of Java installed you might have to delete previous version before you install this.
|
||||||
|
|
||||||
Secondly, you may run list using `run.bat` which will run `list.jar` for you.
|
Secondly, you may run list using `run.bat` which will run `list.jar` for you.
|
||||||
|
|
||||||
## Linux
|
## Linux
|
||||||
### Run list.jar
|
### Run list.jar
|
||||||
Similarly to running list.jar in Windows, you have to first make sure, that you have the appropriate version of Java installed. The program was developed and tested on [JDK Development Kit 21.0.2](https://www.oracle.com/java/technologies/downloads/#java21).
|
Similarly to running list.jar in Windows, you have to first make sure, that you have the appropriate version of Java installed. The program was developed and tested on [JDK Development Kit 21.0.2](https://www.oracle.com/java/technologies/downloads/#java21).
|
||||||
If you already have another version of Java installed you might have to delete previous version before you install this version.
|
If you already have another version of Java installed you might have to delete previous version before you install this.
|
||||||
|
|
||||||
Next, you may run list using `run.sh` which will run `list.jar` for you.
|
Next, you may run list using `run.sh` which will run `list.jar` for you.
|
||||||
|
|
||||||
|
|
18
readme.md
18
readme.md
|
@ -1,10 +1,10 @@
|
||||||
(English version below)
|
(English version below)
|
||||||
|
|
||||||
LIST, korpusni luščilnik
|
LIST, korpusni luščilnik
|
||||||
Različica: 1.0 (Zadnja posodobitev: 21. marec 2019)
|
Različica: 1.3 (Zadnja posodobitev: 28. avgust 2024)
|
||||||
Avtorji: Luka Krsnik, Špela Arhar Holdt, Jaka Čibej, Kaja Dobrovoljc, Aleksander Ključevšek, Simon Krek, Marko Robnik Šikonja
|
Avtorji: Luka Krsnik, Špela Arhar Holdt, Jaka Čibej, Kaja Dobrovoljc, Aleksander Ključevšek, Simon Krek, Marko Robnik Šikonja
|
||||||
|
|
||||||
Korpusni luščilnik LIST je program za luščenje spiskov iz besedilnih korpusov na nivojih znakov, besednih delov, besed in besednih nizov. Nastal je v okviru projekta Nova slovnica sodobne standardne slovenščine: viri in metode (J6-8256), ki ga je med letoma 2017 in 2020 sofinancirala Javna agencija za raziskovalno dejavnost Republike Slovenije iz državnega proračuna. Raziskovalni program Jezikovni viri in tehnologije za slovenski jezik (št. P6-0411) je sofinancirala Javna agencija za raziskovalno dejavnost Republike Slovenije iz državnega proračuna.
|
Korpusni luščilnik LIST je program za luščenje spiskov iz besedilnih korpusov na nivojih znakov, besednih delov, besed in besednih nizov. Nastal je v okviru projektov Nova slovnica sodobne standardne slovenščine: viri in metode (J6-8256), Empirična podlaga za digitalno podprt razvoj pisne jezikovne zmožnosti (J7-3159) in raziskovalnega programa Jezikovni viri in tehnologije za slovenski jezik (št. P6-0411), ki jih financira Javna agencija za znanstvenoraziskovalno in inovacijsko dejavnost Republike Slovenije (ARIS) iz državnega proračuna.
|
||||||
|
|
||||||
Izdajatelj: Center za jezikovne vire in tehnologije Univerze v Ljubljani,
|
Izdajatelj: Center za jezikovne vire in tehnologije Univerze v Ljubljani,
|
||||||
Institut "Jožef Stefan",
|
Institut "Jožef Stefan",
|
||||||
|
@ -15,19 +15,16 @@ Program je dostopen pod licenco MIT License na repozitorijih CLARIN.SI (http://h
|
||||||
|
|
||||||
NAVODILA ZA NAMESTITEV IN ZAGON:
|
NAVODILA ZA NAMESTITEV IN ZAGON:
|
||||||
|
|
||||||
1) Pred uporabo programske opreme mora biti na računalniku nameščena 64-bitna java (https://java.com/en/download/manual.jsp).
|
Datoteko list.zip razširimo in poženemo `list.exe` znotraj razširjene mape. Druge možnosti so opisane v [razširjeni dokumentaciji](instructions.md).
|
||||||
2) Vse tri programske datoteke (run.sh, run.bat, list1.0.jar) skopiramo v poljubno mapo.
|
|
||||||
3) Program zaženemo z dvoklikom na datoteko run.bat na operacijskem sistemu Windows ali run.sh na operacijskem sistemu Linux.
|
|
||||||
4) Ko izbiramo lokacijo korpusa, moramo poskrbeti, da v mapi ni datotek več različnih korpusov.
|
|
||||||
|
|
||||||
|
|
||||||
---------
|
---------
|
||||||
|
|
||||||
LIST – Corpus Extraction Tool
|
LIST – Corpus Extraction Tool
|
||||||
Version: 1.0 (Last update: 21 March 2019)
|
Version: 1.3 (Last update: 28 August 2024)
|
||||||
Authors: Luka Krsnik, Špela Arhar Holdt, Jaka Čibej, Kaja Dobrovoljc, Aleksander Ključevšek, Simon Krek, Marko Robnik Šikonja
|
Authors: Luka Krsnik, Špela Arhar Holdt, Jaka Čibej, Kaja Dobrovoljc, Aleksander Ključevšek, Simon Krek, Marko Robnik Šikonja
|
||||||
|
|
||||||
The LIST corpus extraction tool is a program for extracting lists from text corpora on the levels of characters, word parts, words, and word sets. The program was developed within the New Grammar of Modern Standard Slovene: Resource and Methods project (J6-8256), which was financially supported by the Slovenian Research Agency between 2017 and 2020. The authors acknowledge the financial support from the Slovenian Research Agency (research core funding No. P6-0411 Language Resources and Technologies for Slovene).
|
The LIST corpus extraction tool is a program for extracting lists from text corpora on the levels of characters, word parts, words, and word sets. The program was developed within the New Grammar of Modern Standard Slovene: Resource and Methods project (J6-8256), the Empirical foundations for digitally-supported development of writing skills project (J7-3159) and the Language Resources and Technologies for Slovene programme (P6-0411), all financed by the Slovenian Research and Innovation Agency (ARIS).
|
||||||
|
|
||||||
Publisher: Centre for Language Resources and Technologies, University of Ljubljana,
|
Publisher: Centre for Language Resources and Technologies, University of Ljubljana,
|
||||||
Jožef Stefan Institute,
|
Jožef Stefan Institute,
|
||||||
|
@ -38,7 +35,4 @@ The program is available under the MIT License at CLARIN.SI (http://hdl.handle.n
|
||||||
|
|
||||||
INSTRUCTIONS FOR INSTALLATION AND USE:
|
INSTRUCTIONS FOR INSTALLATION AND USE:
|
||||||
|
|
||||||
1) Make sure that 64-bit java is installed on your computer (https://java.com/en/download/manual.jsp).
|
Extract list.zip file and run list.exe. For other options please read [detailed instructions](instructions.md).
|
||||||
2) Copy all three program files (run.sh, run.bat, list1.0.jar) in a single folder.
|
|
||||||
3) Run the program by double-clicking the run.bat file on a Windows operating system or run.sh on Linux.
|
|
||||||
4) When selecting the location of the corpus, make sure the folder does not include files of multiple different corpora.
|
|
|
@ -44,7 +44,7 @@ public class Messages {
|
||||||
|
|
||||||
// Not properly to be here. TODO move somewhere else in future
|
// Not properly to be here. TODO move somewhere else in future
|
||||||
public static String HELP_URL = "http://slovnica.ijs.si/";
|
public static String HELP_URL = "http://slovnica.ijs.si/";
|
||||||
public static String CJVT_URL = "http://hdl.handle.net/11356/1227";
|
public static String CJVT_URL = "http://hdl.handle.net/11356/1964";
|
||||||
public static String GITHUB_URL = "https://gitea.cjvt.si/lkrsnik/list";
|
public static String GITHUB_URL = "https://gitea.cjvt.si/lkrsnik/list";
|
||||||
|
|
||||||
// helper maps
|
// helper maps
|
||||||
|
|
|
@ -282,8 +282,8 @@ exportFileName.wordSets=word-sets
|
||||||
exportFileName.gram=-gram
|
exportFileName.gram=-gram
|
||||||
exportFileName.skip=-skip
|
exportFileName.skip=-skip
|
||||||
|
|
||||||
about.header=LIST – Corpus Extraction Tool\nVersion: 1.2 (Last update: 18 November 2019)\nAuthors: Luka Krsnik, Špela Arhar Holdt, Jaka Čibej, Kaja Dobrovoljc, Aleksander\n Ključevšek, Simon Krek, Marko Robnik Šikonja
|
about.header=LIST – Corpus Extraction Tool\nVersion: 1.3 (Last update: 28 August 2024)\nAuthors: Luka Krsnik, Špela Arhar Holdt, Jaka Čibej, Kaja Dobrovoljc, Aleksander\n Ključevšek, Simon Krek, Marko Robnik Šikonja
|
||||||
about.description=The LIST corpus extraction tool is a program for extracting lists from text corpora on the\n levels of characters, word parts, words, and word sets. The program was developed within\n the New Grammar of Modern Standard Slovene: Resource and Methods project (J6-8256),\n which was financially supported by the Slovenian Research Agency between 2017 and 2020.\n The authors acknowledge the financial support from the Slovenian Research Agency\n (research core funding No. P6-0411 Language Resources and Technologies for Slovene).\n
|
about.description=The LIST corpus extraction tool is a program for extracting lists from text corpora on the\n levels of characters, word parts, words, and word sets. The program was developed within\n the New Grammar of Modern Standard Slovene: Resource and Methods project (J6-8256),\n the Empirical foundations for digitally-supported development of writing skills project (J7-3159)\n and the Language Resources and Technologies for Slovene programme (P6-0411), all\n financed by the Slovenian Research and Innovation Agency (ARIS).\n
|
||||||
about.signature=Publisher: Centre for Language Resources and Technologies, University of Ljubljana,\nJožef Stefan Institute,\nFaculty of Computer and Information Science, University of Ljubljana
|
about.signature=Publisher: Centre for Language Resources and Technologies, University of Ljubljana,\nJožef Stefan Institute,\nFaculty of Computer and Information Science, University of Ljubljana
|
||||||
about.footer=Maintenance: Centre for Language Resources and Technologies, University of Ljubljana\nThe program is available under the Apache2 licence at CLARIN.si and GitHub.
|
about.footer=Maintenance: Centre for Language Resources and Technologies, University of Ljubljana\nThe program is available under the Apache2 licence at CLARIN.si and GitHub.
|
||||||
about.links=Links:
|
about.links=Links:
|
||||||
|
|
|
@ -282,8 +282,8 @@ exportFileName.wordSets=besedni-nizi
|
||||||
exportFileName.gram=-gram
|
exportFileName.gram=-gram
|
||||||
exportFileName.skip=-preskok
|
exportFileName.skip=-preskok
|
||||||
|
|
||||||
about.header=LIST, korpusni luščilnik\nRazličica: 1.2 (Zadnja posodobitev: 18. november 2019)\nAvtorji: Luka Krsnik, Špela Arhar Holdt, Jaka Čibej, Kaja Dobrovoljc, Aleksander\n Ključevšek, Simon Krek, Marko Robnik Šikonja
|
about.header=LIST, korpusni luščilnik\nRazličica: 1.3 (Zadnja posodobitev: 28. november 2024)\nAvtorji: Luka Krsnik, Špela Arhar Holdt, Jaka Čibej, Kaja Dobrovoljc, Aleksander\n Ključevšek, Simon Krek, Marko Robnik Šikonja
|
||||||
about.description=Korpusni luščilnik LIST je program za luščenje spiskov iz besedilnih korpusov na nivojih\n znakov, besednih delov, besed in besednih nizov. Nastal je v okviru projekta Nova slovnica\n sodobne standardne slovenščine: viri in metode (J6-8256), ki ga je med letoma 2017 in 2020\n sofinancirala Javna agencija za raziskovalno dejavnost Republike Slovenije iz državnega\n proračuna. Raziskovalni program Jezikovni viri in tehnologije za slovenski jezik (št. P6-0411)\n je sofinancirala Javna agencija za raziskovalno dejavnost Republike Slovenije iz državnega\n proračuna.
|
about.description=Korpusni luščilnik LIST je program za luščenje spiskov iz besedilnih korpusov na nivojih\n znakov, besednih delov, besed in besednih nizov. Nastal je v okviru projektov Nova slovnica\n sodobne standardne slovenščine: viri in metode (J6-8256), Empirična podlaga za digitalno\n podprt razvoj pisne jezikovne zmožnosti (J7-3159) in raziskovalnega programa Jezikovni viri\n in tehnologije za slovenski jezik (št. P6-0411), ki jih financira Javna agencija za\n znanstvenoraziskovalno je sofinancirala Javna agencija za raziskovalno dejavnost\n Republike Slovenije iz državnega proračuna.
|
||||||
about.signature=Izdajatelj: Center za jezikovne vire in tehnologije Univerze v Ljubljani,\nInstitut "Jožef Stefan",\nFakulteta za računalništvo in informatiko Univerze v Ljubljani
|
about.signature=Izdajatelj: Center za jezikovne vire in tehnologije Univerze v Ljubljani,\nInstitut "Jožef Stefan",\nFakulteta za računalništvo in informatiko Univerze v Ljubljani
|
||||||
about.footer=Vzdrževanje programa: Center za jezikovne vire in tehnologije Univerze v Ljubljani\nProgram je dostopen pod licenco Apache2 na repozitorijih CLARIN.si in GitHub.
|
about.footer=Vzdrževanje programa: Center za jezikovne vire in tehnologije Univerze v Ljubljani\nProgram je dostopen pod licenco Apache2 na repozitorijih CLARIN.si in GitHub.
|
||||||
about.links=Povezave:
|
about.links=Povezave:
|
||||||
|
|
Loading…
Reference in New Issue
Block a user