TheAnachronism/docspell
1
0
Fork 0
mirror of https://github.com/TheAnachronism/docspell.git synced 2025-06-22 02:18:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

Reformat with scalafmt 3.0.0

Browse Source
This commit is contained in:
Scala Steward
2021-08-19 08:50:30 +02:00
parent 5a2a0295ef
commit e4fecefaea
127 changed files with 558 additions and 658 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
modules/extract/src/main/scala/docspell/extract/ocr/Ocr.scala
View File

@ -62,8 +62,8 @@ object Ocr {
): Stream[F, String] =
runTesseractFile(img, logger, lang, config)
/** Run ghostscript to extract all pdf pages into tiff files. The
* files are stored to a temporary location on disk and returned.
/** Run ghostscript to extract all pdf pages into tiff files. The files are stored to a
* temporary location on disk and returned.
*/
private[extract] def runGhostscript[F[_]: Async](
pdf: Stream[F, Byte],
@ -88,8 +88,8 @@ object Ocr {
.flatMap(_ => File.listFiles(pathEndsWith(".tif"), wd))
}
/** Run ghostscript to extract all pdf pages into tiff files. The
* files are stored to a temporary location on disk and returned.
/** Run ghostscript to extract all pdf pages into tiff files. The files are stored to a
* temporary location on disk and returned.
*/
private[extract] def runGhostscriptFile[F[_]: Async](
pdf: Path,
@ -111,8 +111,8 @@ object Ocr {
private def pathEndsWith(ext: String): Path => Boolean =
p => p.fileName.toString.endsWith(ext)
/** Run unpaper to optimize the image for ocr. The
* files are stored to a temporary location on disk and returned.
/** Run unpaper to optimize the image for ocr. The files are stored to a temporary
* location on disk and returned.
*/
private[extract] def runUnpaperFile[F[_]: Async](
img: Path,
@ -139,8 +139,7 @@ object Ocr {
}
}
/** Run tesseract on the given image file and return the extracted
* text.
/** Run tesseract on the given image file and return the extracted text.
*/
private[extract] def runTesseractFile[F[_]: Async](
img: Path,
@ -160,8 +159,7 @@ object Ocr {
.map(_.stdout)
}
/** Run tesseract on the given image file and return the extracted
* text.
/** Run tesseract on the given image file and return the extracted text.
*/
private[extract] def runTesseractStdin[F[_]: Async](
img: Stream[F, Byte],

4
modules/extract/src/main/scala/docspell/extract/ocr/TextExtract.scala
View File

@ -31,7 +31,7 @@ object TextExtract {
): Stream[F, Text] =
Stream
.eval(TikaMimetype.detect(in, MimeTypeHint.none))
.flatMap({
.flatMap {
case MimeType.pdf =>
Stream.eval(Ocr.extractPdf(in, logger, lang, config)).unNoneTerminate
@ -40,7 +40,7 @@ object TextExtract {
case mt =>
raiseError(s"File `$mt` not supported")
})
}
.map(Text.apply)
private def raiseError[F[_]: Sync](msg: String): Stream[F, Nothing] =

16
modules/extract/src/main/scala/docspell/extract/poi/PoiExtract.scala
View File

@ -49,17 +49,13 @@ object PoiExtract {
case PoiType.docx =>
getDocx(data)
case PoiType.msoffice =>
EitherT(getDoc[F](data))
.recoverWith({ case _ =>
EitherT(getXls[F](data))
})
.value
EitherT(getDoc[F](data)).recoverWith { case _ =>
EitherT(getXls[F](data))
}.value
case PoiType.ooxml =>
EitherT(getDocx[F](data))
.recoverWith({ case _ =>
EitherT(getXlsx[F](data))
})
.value
EitherT(getDocx[F](data)).recoverWith { case _ =>
EitherT(getXlsx[F](data))
}.value
case mt =>
Sync[F].pure(Left(new Exception(s"Unsupported content: ${mt.asString}")))
}