Use ocrmypdf tool to create pdf/a during conversion

- Use another external tool to convert pdf to pdf which also adds the
  extracted text as another layer into the pdf

- Although not used, the external conversion routine will now check
  for an existing text file that is named as the pdf file with extension
  `.txt`. If present it is included in the conversion result and will be
  used as the extracted text.

- text extraction for pdf files happens now on the converted file,
  because it may already contain the text from the conversion step and
  thus avoids running OCR twice.

- All errors during conversion are not fatal; processing continues
  without a converted file.

modules/joex/src/main/resources/reference.conf

@@ -339,6 +339,39 @@ docspell.joex {
       }
       working-dir = ${java.io.tmpdir}"/docspell-convert"
     }
+
+    # The tool ocrmypdf can be used to convert pdf files to pdf files
+    # in order to add extracted text as a separate layer. This makes
+    # image-only pdfs searchable and you can select and copy/paste the
+    # text. It also converts pdfs into pdf/a type pdfs, which are best
+    # suited for archiving. So it makes sense to use this even for
+    # text-only pdfs.
+    #
+    # It is recommended to install ocrympdf, but it also is optional.
+    # If it is enabled but fails, the error is not fatal and the
+    # processing will continue using the original pdf for extracting
+    # text. You can also disable it to remove the errors from the
+    # processing logs.
+    #
+    # The `--skip-text` option is necessary to not fail on "text" pdfs
+    # (where ocr is not necessary). In this case, the pdf will be
+    # converted to PDF/A.
+    ocrmypdf = {
+      enabled = true
+      command = {
+        program = "ocrmypdf"
+        args = [
+          "-l", "{{lang}}",
+          "--skip-text",
+          "--deskew",
+          "-j", "1",
+          "{{infile}}",
+          "{{outfile}}"
+        ]
+        timeout = "5 minutes"
+      }
+      working-dir = ${java.io.tmpdir}"/docspell-convert"
+    }
   }
 
   # General config for processing documents

modules/joex/src/main/scala/docspell/joex/process/ConvertPdf.scala

@@ -64,10 +64,6 @@ object ConvertPdf {
   )(ra: RAttachment, mime: Mimetype): F[(RAttachment, Option[RAttachmentMeta])] =
     Conversion.create[F](cfg, sanitizeHtml, ctx.blocker, ctx.logger).use { conv =>
       mime.toLocal match {
-        case MimeType.PdfMatch(_) =>
-          ctx.logger.debug(s"Not going to convert a PDF file ${ra.name} into a PDF.") *>
-            (ra, None: Option[RAttachmentMeta]).pure[F]
-
         case mt =>
           val data = ctx.store.bitpeace
             .get(ra.fileId.id)

modules/joex/src/main/scala/docspell/joex/process/TextExtraction.scala

@@ -85,9 +85,10 @@ object TextExtraction {
       item: ItemData
   )(ra: RAttachment): F[RAttachmentMeta] =
     for {
-      _   <- ctx.logger.debug(s"Extracting text for attachment ${stripAttachmentName(ra)}")
-      dst <- Duration.stopTime[F]
-      txt <- extractTextFallback(ctx, cfg, ra, lang)(filesToExtract(item, ra))
+      _    <- ctx.logger.debug(s"Extracting text for attachment ${stripAttachmentName(ra)}")
+      dst  <- Duration.stopTime[F]
+      fids <- filesToExtract(ctx)(item, ra)
+      txt  <- extractTextFallback(ctx, cfg, ra, lang)(fids)
       meta = item.changeMeta(
         ra.id,
         rm => rm.setContentIfEmpty(txt.map(_.trim).filter(_.nonEmpty))
@@ -151,11 +152,24 @@ object TextExtraction {
 
   /** Returns the fileIds to extract text from. First, the source file
     * is tried. If that fails, the converted file is tried.
+    *
+    * If the source file is a PDF, then use the converted file. This
+    * may then already contain the text if ocrmypdf is enabled. If it
+    * is disabled, both files are the same.
     */
-  private def filesToExtract(item: ItemData, ra: RAttachment): List[Ident] =
+  private def filesToExtract[F[_]: Sync](ctx: Context[F, _])(
+      item: ItemData,
+      ra: RAttachment
+  ): F[List[Ident]] =
     item.originFile.get(ra.id) match {
-      case Some(sid) => List(sid, ra.fileId).distinct
-      case None      => List(ra.fileId)
+      case Some(sid) =>
+        ctx.store.transact(RFileMeta.findMime(sid)).map {
+          case Some(MimeType.PdfMatch(_)) =>
+            List(ra.fileId)
+          case _ =>
+            List(sid, ra.fileId).distinct
+        }
+      case None => List(ra.fileId).pure[F]
     }
 
   private def stripAttachmentName(ra: RAttachment): String =