From b12d965223eda87a1660ed4bcc4655596002be34 Mon Sep 17 00:00:00 2001
From: Eike Kettner <eike.kettner@posteo.de>
Date: Wed, 20 Jan 2021 00:40:58 +0100
Subject: [PATCH] Improve logging

---
 .../src/main/scala/docspell/joex/learn/Classify.scala     | 4 +++-
 .../main/scala/docspell/joex/process/TextAnalysis.scala   | 6 +++---
 .../main/scala/docspell/joex/process/TextExtraction.scala | 8 ++++++--
 3 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/modules/joex/src/main/scala/docspell/joex/learn/Classify.scala b/modules/joex/src/main/scala/docspell/joex/learn/Classify.scala
index 4c65556c..4d4c2676 100644
--- a/modules/joex/src/main/scala/docspell/joex/learn/Classify.scala
+++ b/modules/joex/src/main/scala/docspell/joex/learn/Classify.scala
@@ -25,8 +25,9 @@ object Classify {
       text: String
   )(cname: ClassifierName): F[Option[String]] =
     (for {
-      _     <- OptionT.liftF(logger.info(s"Guessing label for ${cname.name} …"))
+      _ <- OptionT.liftF(logger.info(s"Guessing label for ${cname.name} …"))
       model <- OptionT(store.transact(RClassifierModel.findByName(coll, cname.name)))
+        .flatTapNone(logger.debug("No classifier model found."))
       modelData =
         store.bitpeace
           .get(model.fileId.id)
@@ -40,6 +41,7 @@ object Classify {
           .drain
           .flatMap(_ => classifier.classify(logger, ClassifierModel(modelFile), text))
       }).filter(_ != LearnClassifierTask.noClass)
+        .flatTapNone(logger.debug("Guessed: <none>"))
       _ <- OptionT.liftF(logger.debug(s"Guessed: ${cls}"))
     } yield cls).value
 
diff --git a/modules/joex/src/main/scala/docspell/joex/process/TextAnalysis.scala b/modules/joex/src/main/scala/docspell/joex/process/TextAnalysis.scala
index a3c4edb5..33ec72d6 100644
--- a/modules/joex/src/main/scala/docspell/joex/process/TextAnalysis.scala
+++ b/modules/joex/src/main/scala/docspell/joex/process/TextAnalysis.scala
@@ -37,8 +37,7 @@ object TextAnalysis {
         _ <- t.traverse(m =>
           ctx.store.transact(RAttachmentMeta.updateLabels(m._1.id, m._1.nerlabels))
         )
-        e <- s
-        _ <- ctx.logger.info(s"Text-Analysis finished in ${e.formatExact}")
+
         v = t.toVector
         autoTagEnabled <- getActiveAutoTag(ctx, cfg)
         tag <-
@@ -50,6 +49,8 @@ object TextAnalysis {
             predictItemEntities(ctx, cfg, item.metas, analyser.classifier)
           else MetaProposalList.empty.pure[F]
 
+        e <- s
+        _ <- ctx.logger.info(s"Text-Analysis finished in ${e.formatExact}")
       } yield item
         .copy(
           metas = v.map(_._1),
@@ -109,7 +110,6 @@ object TextAnalysis {
         mtype: MetaProposalType
     ): F[Option[MetaProposal]] =
       for {
-        _     <- ctx.logger.debug(s"Guessing $mtype using classifier")
         label <- makeClassify(ctx, cfg, classifier)(text).apply(cname)
       } yield label.map(str =>
         MetaProposal(mtype, Candidate(IdRef(Ident.unsafe(""), str), Set.empty))
diff --git a/modules/joex/src/main/scala/docspell/joex/process/TextExtraction.scala b/modules/joex/src/main/scala/docspell/joex/process/TextExtraction.scala
index fee7d323..80b4b13e 100644
--- a/modules/joex/src/main/scala/docspell/joex/process/TextExtraction.scala
+++ b/modules/joex/src/main/scala/docspell/joex/process/TextExtraction.scala
@@ -46,10 +46,14 @@ object TextExtraction {
         )
         _   <- fts.indexData(ctx.logger, (idxItem +: txt.map(_.td)).toSeq: _*)
         dur <- start
-        _   <- ctx.logger.info(s"Text extraction finished in ${dur.formatExact}")
+        extractedTags = txt.flatMap(_.tags).distinct.toList
+        _ <- ctx.logger.info(s"Text extraction finished in ${dur.formatExact}.")
+        _ <-
+          if (extractedTags.isEmpty) ().pure[F]
+          else ctx.logger.debug(s"Found tags in file: $extractedTags")
       } yield item
         .copy(metas = txt.map(_.am))
-        .appendTags(txt.flatMap(_.tags).distinct.toList)
+        .appendTags(extractedTags)
     }
 
   // --  helpers