Early draft for text extraction

This commit is contained in:
Eike Kettner
2020-02-17 01:57:22 +01:00
parent 1a5546fe99
commit 3d615181e0
22 changed files with 287 additions and 45 deletions

View File

@ -0,0 +1,25 @@
package docspell.files
import cats.effect.{Blocker, ExitCode, IO, IOApp}
import docspell.common.MimeTypeHint
import scala.concurrent.ExecutionContext
object Playing extends IOApp {
val blocker = Blocker.liftExecutionContext(ExecutionContext.global)
def run(args: List[String]): IO[ExitCode] = IO {
//val ods = ExampleFiles.examples_sample_ods.readURL[IO](8192, blocker)
//val odt = ExampleFiles.examples_sample_odt.readURL[IO](8192, blocker)
val rtf = ExampleFiles.examples_sample_rtf.readURL[IO](8192, blocker)
val x = for {
odsm1 <- TikaMimetype.detect(rtf,
MimeTypeHint.filename(ExampleFiles.examples_sample_rtf.path.segments.last))
odsm2 <- TikaMimetype.detect(rtf, MimeTypeHint.none)
} yield (odsm1, odsm2)
println(x.unsafeRunSync())
ExitCode.Success
}
}