TheAnachronism/docspell
1
0
Fork 0
mirror of https://github.com/TheAnachronism/docspell.git synced 2025-06-22 18:38:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

Use collective's addressbook to configure regexner

Browse Source
This commit is contained in:
Eike Kettner
2020-08-24 14:35:56 +02:00
parent 8628a0a8b3
commit 96d2f948f2
4 changed files with 84 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
modules/analysis/src/test/scala/docspell/analysis/nlp/TextAnalyserSuite.scala
View File

@ -3,12 +3,17 @@ package docspell.analysis.nlp
import minitest.SimpleTestSuite
import docspell.files.TestFiles
import docspell.common._
import edu.stanford.nlp.pipeline.StanfordCoreNLP
object TextAnalyserSuite extends SimpleTestSuite {
lazy val germanClassifier =
new StanfordCoreNLP(Properties.nerGerman(None, false))
lazy val englishClassifier =
new StanfordCoreNLP(Properties.nerEnglish(None))
test("find english ner labels") {
val labels =
StanfordNerClassifier.nerAnnotate(Language.English)(TestFiles.letterENText)
StanfordNerClassifier.runClassifier(englishClassifier, TestFiles.letterENText)
val expect = Vector(
NerLabel("Derek", NerTag.Person, 0, 5),
NerLabel("Jeter", NerTag.Person, 6, 11),
@ -44,7 +49,7 @@ object TextAnalyserSuite extends SimpleTestSuite {
test("find german ner labels") {
val labels =
StanfordNerClassifier.nerAnnotate(Language.German)(TestFiles.letterDEText)
StanfordNerClassifier.runClassifier(germanClassifier, TestFiles.letterDEText)
val expect = Vector(
NerLabel("Max", NerTag.Person, 0, 3),
NerLabel("Mustermann", NerTag.Person, 4, 14),