TheAnachronism/docspell
1
0
Fork 0
mirror of https://github.com/TheAnachronism/docspell.git synced 2025-03-25 16:45:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix potential index-out-of-bounds error in classifier

Browse Source 
The stanford library expects a non-empty text.
This commit is contained in:
Eike Kettner 2020-11-09 00:04:13 +01:00
parent 709848244c
commit cf6e63785d
1 changed files with 12 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
modules/analysis/src/main/scala/docspell/analysis/nlp/StanfordTextClassifier.scala
View File

@ -37,14 +37,19 @@ final class StanfordTextClassifier[F[_]: Sync: ContextShift](
def classify(
logger: Logger[F],
model: ClassifierModel,
text: String
txt: String
): F[Option[String]] =
Sync[F].delay {
val cls = ColumnDataClassifier.getClassifier(
model.model.normalize().toAbsolutePath().toString()
)
val cat = cls.classOf(cls.makeDatumFromLine("\t\t" + normalisedText(text)))
Option(cat)
Option(txt).map(_.trim).filter(_.nonEmpty) match {
case Some(text) =>
Sync[F].delay {
val cls = ColumnDataClassifier.getClassifier(
model.model.normalize().toAbsolutePath().toString()
)
val cat = cls.classOf(cls.makeDatumFromLine("\t\t" + normalisedText(text)))
Option(cat)
}
case None =>
(None: Option[String]).pure[F]
}
// --- helpers