From 414101fc7a944d5df0f265e1958086b929e90a3b Mon Sep 17 00:00:00 2001
From: Clemens Schmid <nevromecs@gmail.com>
Date: Tue, 21 Jul 2026 13:50:29 +0200
Subject: [PATCH 01/11] ignore hidden directories when reading entire package
 collections/archives

---
 src/Poseidon/Core/Package.hs | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/src/Poseidon/Core/Package.hs b/src/Poseidon/Core/Package.hs
index 9f9efc87..f7e7a546 100644
--- a/src/Poseidon/Core/Package.hs
+++ b/src/Poseidon/Core/Package.hs
@@ -709,11 +709,16 @@ checkJannoBibConsistency pacName (JannoRows rows) bibtex = do
 findAllPoseidonYmlFiles :: FilePath -> IO [FilePath]
 findAllPoseidonYmlFiles baseDir = do
     entries <- listDirectory baseDir
-    let posFiles = map (baseDir </>) $ filter (=="POSEIDON.yml") $ map takeFileName entries
-    subDirs <- filterM doesDirectoryExist . map (baseDir </>) $ entries
+    let posFiles = map (baseDir </>) $ filter (=="POSEIDON.yml") entries
+    subDirs <- filterM doesDirectoryExist . map (baseDir </>) $ filter (not . isHidden) entries
     morePosFiles <- fmap concat . mapM findAllPoseidonYmlFiles $ subDirs
     return $ posFiles ++ morePosFiles
 
+isHidden :: FilePath -> Bool
+isHidden p = case takeFileName p of
+    '.':_ -> True
+    _     -> False
+
 -- | A function to read genotype data jointly from multiple packages
 getJointGenotypeData :: MonadSafe m =>
                         LogA -- ^ how messages should be logged

From a1f0fe4eb8a38eec1e56b1189e997ee17f377157 Mon Sep 17 00:00:00 2001
From: Clemens Schmid <nevromecs@gmail.com>
Date: Thu, 23 Jul 2026 11:19:10 +0200
Subject: [PATCH 02/11] html api: made display of description and source url
 indendent of each other

---
 src/Poseidon/Core/ServerHTML.hs | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/src/Poseidon/Core/ServerHTML.hs b/src/Poseidon/Core/ServerHTML.hs
index 63c635b2..89aa0f0b 100644
--- a/src/Poseidon/Core/ServerHTML.hs
+++ b/src/Poseidon/Core/ServerHTML.hs
@@ -159,10 +159,13 @@ mainPage pacsPerArchive = do
               H.a ! A.href ("/explorer/" <>  H.toValue archiveName <> "/" <> H.toValue pacName) $ H.toMarkup pacNameVersion
               H.toMarkup $ H.string $ " (" ++  maybe "?" show (posPacLastModified pac) ++ "); "
         -- archives with more info
-        case (maybeDescription,maybeURL) of
-          (Just desc, Just url) -> do
+        case maybeDescription of
+          Just desc -> do
             H.br
             H.p $ H.toMarkup desc
+          _ -> return ()
+        case maybeURL of
+          Just url -> do
             H.footer $ H.p $ H.a
               ! A.href (H.stringValue url)
               ! A.style "float: right; font-size: 0.8em;" $

From 537fac0d039ee96cb97769b3c8158f96716a292e Mon Sep 17 00:00:00 2001
From: Clemens Schmid <nevromecs@gmail.com>
Date: Thu, 23 Jul 2026 11:30:33 +0200
Subject: [PATCH 03/11] html api: make source column hide when url missing

---
 src/Poseidon/Core/ServerHTML.hs | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/src/Poseidon/Core/ServerHTML.hs b/src/Poseidon/Core/ServerHTML.hs
index 89aa0f0b..7cca56aa 100644
--- a/src/Poseidon/Core/ServerHTML.hs
+++ b/src/Poseidon/Core/ServerHTML.hs
@@ -238,7 +238,9 @@ archivePage archiveName maybeArchiveSpecURL excludeFromMap plotSamples pacs = do
             H.th $ H.b "Package"
             H.th $ H.b "# Samples"
             H.th $ H.b "Last modified"
-            H.th $ H.b "Source"
+            case maybeArchiveSpecURL of
+                Just _  -> H.th $ H.b "Source"
+                Nothing -> return ()
             H.th $ H.b ".zip Archive"
       forM_ pacs $ \pac -> do
         let pacName = getPacName pac
@@ -253,8 +255,8 @@ archivePage archiveName maybeArchiveSpecURL excludeFromMap plotSamples pacs = do
             Nothing -> H.td $ H.string "n/a"
           -- archives with more info
           case maybeArchiveSpecURL of
-            Just url -> H.td $ H.a ! A.href (H.stringValue url <> "/" <> H.toValue pacName) $ H.toMarkup ("GitHub" :: String)
-            Nothing  -> H.td $ H.string "n/a"
+            Just url -> H.td $ H.a ! A.href (H.stringValue url <> "/" <> H.toValue pacName) $ H.toMarkup ("URL" :: String)
+            Nothing  -> return ()
           H.td $ H.a ! A.href ("/zip_file/" <> H.toValue pacName <> "?archive=" <> H.toValue archiveName) $ H.toMarkup ("Download" :: String)
 
 packageVersionPage ::

From da4b195bdbc08cc24764edc7303f6942c0cb6a2b Mon Sep 17 00:00:00 2001
From: Clemens Schmid <clemens@nevrome.de>
Date: Sun, 26 Jul 2026 22:24:54 +0200
Subject: [PATCH 04/11] implemented line ending validation with a warning as
 discussed in #311

---
 src/Poseidon/CLI/Trident/Forge.hs |  4 +--
 src/Poseidon/CLI/Trident/Init.hs  |  2 +-
 src/Poseidon/Core/Package.hs      | 27 ++++++++++++++-----
 src/Poseidon/Core/Utils.hs        | 43 +++++++++++++++++++++++++++----
 4 files changed, 62 insertions(+), 14 deletions(-)

diff --git a/src/Poseidon/CLI/Trident/Forge.hs b/src/Poseidon/CLI/Trident/Forge.hs
index b3b40336..d7551353 100644
--- a/src/Poseidon/CLI/Trident/Forge.hs
+++ b/src/Poseidon/CLI/Trident/Forge.hs
@@ -273,7 +273,7 @@ runForge (
                 (Just path) -> do
                     logInfo "Copying README file from source package"
                     let fullSourcePath = posPacBaseDir pacSource </> path
-                    liftIO $ checkFile fullSourcePath Nothing
+                    checkFile fullSourcePath Nothing
                     liftIO $ copyFile fullSourcePath $ outPath </> path
         copyCHANGELOGFile :: FilePath -> PoseidonPackage -> PoseidonIO ()
         copyCHANGELOGFile outPath pacSource = do
@@ -282,7 +282,7 @@ runForge (
                 (Just path) -> do
                     logInfo "Copying CHANGELOG file from source package"
                     let fullSourcePath = posPacBaseDir pacSource </> path
-                    liftIO $ checkFile fullSourcePath Nothing
+                    checkFile fullSourcePath Nothing
                     liftIO $ copyFile fullSourcePath $ outPath </> path
         compileGenotypeData :: FilePath -> GenotypeFileSpec -> [PoseidonPackage] -> [Int] -> PoseidonIO (VUM.IOVector Int)
         compileGenotypeData outPath gFileSpec relevantPackages relevantIndices = do
diff --git a/src/Poseidon/CLI/Trident/Init.hs b/src/Poseidon/CLI/Trident/Init.hs
index 754ab8cf..ca8bb93f 100644
--- a/src/Poseidon/CLI/Trident/Init.hs
+++ b/src/Poseidon/CLI/Trident/Init.hs
@@ -43,7 +43,7 @@ runInit (InitOptions genotypeDataIn outPathRaw maybeOutName minimal) = do
             GenotypePlink      genoFile _ snpFile _ indFile _ -> [genoFile, snpFile, indFile]
             GenotypeVCF        vcfFile  _                     -> [vcfFile]
     forM_ sourceFiles $ \sourceFile -> do
-        liftIO $ checkFile sourceFile Nothing
+        checkFile sourceFile Nothing
         let targetFile = outPath </> takeFileName sourceFile
         liftIO $ copyFile sourceFile targetFile
     -- create new package
diff --git a/src/Poseidon/Core/Package.hs b/src/Poseidon/Core/Package.hs
index f7e7a546..eac95537 100644
--- a/src/Poseidon/Core/Package.hs
+++ b/src/Poseidon/Core/Package.hs
@@ -82,6 +82,8 @@ import           Poseidon.Core.ServerClient     (AddColSpec (..),
                                                  PackageInfo (..))
 import           Poseidon.Core.Utils            (LogA, PoseidonException (..),
                                                  PoseidonIO, checkFile,
+                                                 checkLineEnding,
+                                                 checkLineEndingIfNotZipped,
                                                  envErrorLength, envLogAction,
                                                  logDebug, logError, logInfo,
                                                  logWarning, logWithEnv,
@@ -443,7 +445,7 @@ readPoseidonPackage opts ymlPath = do
     checkYML yml
 
     -- file existence and checksum test
-    liftIO $ checkFiles baseDir (_readOptIgnoreChecksums opts) (_readOptIgnoreGeno opts) yml
+    checkFiles baseDir (_readOptIgnoreChecksums opts) (_readOptIgnoreGeno opts) yml
 
     -- read janno (or fill with empty dummy object)
     indEntries <- loadIndividuals baseDir geno
@@ -552,7 +554,7 @@ validateForge pacs strandcheck = do
         ) (throwIO . PoseidonGenotypeExceptionForward errLength)
 
 -- throws exception if any file is missing or checksum is incorrect
-checkFiles :: FilePath -> Bool -> Bool -> PoseidonYamlStruct -> IO ()
+checkFiles :: FilePath -> Bool -> Bool -> PoseidonYamlStruct -> PoseidonIO ()
 checkFiles baseDir ignoreChecksums ignoreGenotypeFilesMissing yml = do
     -- Check README File
     case poseidonReadmeFilePath baseDir yml of
@@ -567,19 +569,25 @@ checkFiles baseDir ignoreChecksums ignoreGenotypeFilesMissing yml = do
         Nothing -> return ()
         Just fn -> if ignoreChecksums
                    then checkFile fn Nothing
-                   else checkFile fn $ _posYamlBibFileChkSum yml
+                   else do
+                       checkLineEnding fn
+                       checkFile fn $ _posYamlBibFileChkSum yml
     -- Check Janno File
     case poseidonJannoFilePath baseDir yml of
         Nothing -> return ()
         Just fn -> if ignoreChecksums
                    then checkFile fn Nothing
-                   else checkFile fn $ _posYamlJannoFileChkSum yml
+                   else do
+                       checkLineEnding fn
+                       checkFile fn $ _posYamlJannoFileChkSum yml
     -- Check SeqSource File
     case poseidonSeqSourceFilePath baseDir yml of
         Nothing -> return ()
         Just fn -> if ignoreChecksums
                    then checkFile fn Nothing
-                   else checkFile fn $ _posYamlSeqSourceFileChkSum yml
+                   else do
+                       checkLineEnding fn
+                       checkFile fn $ _posYamlSeqSourceFileChkSum yml
     -- Check Genotype files
     unless ignoreGenotypeFilesMissing $ do
         let gd = _posYamlGenotypeData yml
@@ -592,8 +600,11 @@ checkFiles baseDir ignoreChecksums ignoreGenotypeFilesMissing yml = do
                     checkFile (d </> snpF)  Nothing
                     checkFile (d </> indF)  Nothing
                 else do
+                    checkLineEndingIfNotZipped (d </> genoF)
                     checkFile (d </> genoF) genoFc
+                    checkLineEndingIfNotZipped (d </> snpF)
                     checkFile (d </> snpF)  snpFc
+                    checkLineEndingIfNotZipped (d </> indF)
                     checkFile (d </> indF)  indFc
             GenotypePlink genoF genoFc snpF snpFc indF indFc -> do
                 if ignoreChecksums
@@ -603,12 +614,16 @@ checkFiles baseDir ignoreChecksums ignoreGenotypeFilesMissing yml = do
                     checkFile (d </> indF)  Nothing
                 else do
                     checkFile (d </> genoF) genoFc
+                    checkLineEndingIfNotZipped (d </> snpF)
                     checkFile (d </> snpF)  snpFc
+                    checkLineEndingIfNotZipped (d </> indF)
                     checkFile (d </> indF)  indFc
             GenotypeVCF genoF genoFc -> do
                 if ignoreChecksums
                 then checkFile (d </> genoF) Nothing
-                else checkFile (d </> genoF) genoFc
+                else do
+                    checkLineEndingIfNotZipped (d </> genoF)
+                    checkFile (d </> genoF) genoFc
 
 -- the last flag is important for reading VCFs, which can lack group and sex information.
 checkJannoIndConsistency :: String -> JannoRows -> [EigenstratIndEntry] -> Bool -> IO ()
diff --git a/src/Poseidon/Core/Utils.hs b/src/Poseidon/Core/Utils.hs
index 0bd36d60..81e0e1d5 100644
--- a/src/Poseidon/Core/Utils.hs
+++ b/src/Poseidon/Core/Utils.hs
@@ -12,6 +12,8 @@ module Poseidon.Core.Utils (
     envErrorLength,
     LogMode (..),
     checkFile,
+    checkLineEnding,
+    checkLineEndingIfNotZipped,
     getChecksum,
     logWarning,
     logInfo,
@@ -38,17 +40,20 @@ import           Colog                  (HasLog (..), LogAction (..), Message,
                                          msgText, showSeverity)
 import           Control.Exception      (Exception (..), throwIO)
 import           Control.Exception.Base (SomeException)
-import           Control.Monad          (when)
+import           Control.Monad          (unless, when)
 import           Control.Monad.Catch    (throwM)
 import           Control.Monad.IO.Class (MonadIO, liftIO)
 import           Control.Monad.Reader   (ReaderT, asks, runReaderT)
+import qualified Data.ByteString        as BS
 import qualified Data.ByteString.Lazy   as LB
 import           Data.Digest.Pure.MD5   (md5)
+import           Data.List              (isSuffixOf)
 import qualified Data.Set               as Set
 import           Data.Text              (Text, pack)
 import           Data.Time              (defaultTimeLocale, formatTime,
                                          getCurrentTime, utcToLocalZonedTime)
 import           Data.Version           (showVersion)
+import           Data.Word              (Word8)
 import           Data.Yaml              (ParseException,
                                          prettyPrintParseException)
 import           GHC.Stack              (callStack, withFrozenCallStack)
@@ -56,9 +61,9 @@ import           Network.HTTP.Conduit   (HttpException (..))
 import           SequenceFormats.Plink  (PlinkPopNameMode (..))
 import           System.Directory       (doesFileExist)
 import           System.FilePath.Posix  (takeBaseName)
+import           System.IO              (IOMode (..), withBinaryFile)
 import qualified Text.Parsec.Error      as P
 
-
 type LogA = LogAction IO Message
 
 data TestMode = Testing | Production deriving Show
@@ -279,16 +284,16 @@ renderPoseidonException PoseidonCantPreserveException =
     "Can't use --preserve if there is more than one relevant source package."
 
 -- helper function to check if a file exists
-checkFile :: FilePath -> Maybe String -> IO ()
+checkFile :: FilePath -> Maybe String -> PoseidonIO ()
 checkFile fn maybeChkSum = do
-    fe <- doesFileExist fn
+    fe <- liftIO $ doesFileExist fn
     if not fe
     then throwM (PoseidonFileExistenceException fn)
     else
         case maybeChkSum of
             Nothing -> return ()
             Just chkSum -> do
-                fnChkSum <- getChecksum fn
+                fnChkSum <- liftIO $ getChecksum fn
                 when (fnChkSum /= chkSum) $ throwM (PoseidonFileChecksumException fn)
 
 -- helper functions to get the checksum of a file
@@ -298,6 +303,34 @@ getChecksum f = do
     let md5Digest = md5 fileContent
     return $ show md5Digest
 
+-- helper function to check line endings of text files
+-- only considers the first line:
+-- if the byte immediately before the first LF is CR,
+-- then the first line uses CRLF; otherwise it uses plain Unix LF
+checkLineEnding :: FilePath -> PoseidonIO ()
+checkLineEnding fn =
+  liftIO (withBinaryFile fn ReadMode $ \h -> go h Nothing) >>= \isCRLF ->
+    when isCRLF $ logWarning $ "File " <> fn <> " appears to use CRLF (Windows) line endings."
+  where
+    go h prev = do
+      chunk <- BS.hGetSome h 8192
+      if BS.null chunk
+        then pure False
+        else case BS.elemIndex lf chunk of
+          Just i ->
+              if i > 0
+              then pure $ BS.index chunk (i - 1) == cr
+              else pure $ prev == Just cr
+          Nothing ->
+            go h (Just $ BS.last chunk)
+
+lf, cr :: Word8
+lf = 10 -- '\n'
+cr = 13 -- '\r'
+
+checkLineEndingIfNotZipped :: FilePath -> PoseidonIO ()
+checkLineEndingIfNotZipped fn = unless (".gz" `isSuffixOf` fn) $ checkLineEnding fn
+
 -- helper functions to pad and cut strings
 padRight :: Int -> String -> String
 padRight n s

From a64cd4c9a77fea5d43bd3d71b08a9a51b66583d0 Mon Sep 17 00:00:00 2001
From: Clemens Schmid <clemens@nevrome.de>
Date: Mon, 27 Jul 2026 22:52:37 +0200
Subject: [PATCH 05/11] allow ORCIDs in rectify --newContributors; solves #330
 when merged

---
 poseidon-hs.cabal                             |  1 +
 .../CLI/Trident/OptparseApplicativeParsers.hs |  4 +-
 src/Poseidon/Core/Contributor.hs              | 10 ++---
 test/Poseidon/Core/ContributorSpec.hs         | 37 +++++++++++++++++++
 4 files changed, 45 insertions(+), 7 deletions(-)
 create mode 100644 test/Poseidon/Core/ContributorSpec.hs

diff --git a/poseidon-hs.cabal b/poseidon-hs.cabal
index f83965c4..ae2c1040 100644
--- a/poseidon-hs.cabal
+++ b/poseidon-hs.cabal
@@ -85,6 +85,7 @@ Test-Suite poseidon-tools-tests
                         Poseidon.Core.MathHelpersSpec, Poseidon.Core.JannocoalesceSpec, Poseidon.Core.SummariseSpec,
                         Poseidon.Core.SurveySpec, Poseidon.Core.GenotypeDataSpec, Poseidon.Core.EntitiesListSpec,
                         Poseidon.Core.ChronicleSpec, Poseidon.Core.SequencingSourceSpec, Poseidon.Core.InterfaceSpec,
+                        Poseidon.Core.ContributorSpec
                         -- analysis
                         Poseidon.Analysis.FStatsSpec, Poseidon.Analysis.UtilsSpec
     default-language:   Haskell2010
diff --git a/src/Poseidon/CLI/Trident/OptparseApplicativeParsers.hs b/src/Poseidon/CLI/Trident/OptparseApplicativeParsers.hs
index aa20f731..48681602 100644
--- a/src/Poseidon/CLI/Trident/OptparseApplicativeParsers.hs
+++ b/src/Poseidon/CLI/Trident/OptparseApplicativeParsers.hs
@@ -234,7 +234,7 @@ parseMaybeContributors = OP.option (Just <$> OP.eitherReader readContributorStri
     OP.long "newContributors" <>
     OP.metavar "DSL" <>
     OP.help "Contributors to add to the POSEIDON.yml file \
-            \ in the form \"[Firstname Lastname](Email address);...\"." <>
+            \ in the form \"[Firstname Lastname](Email address)<ORCID>;...\". The ORCIDs are optional." <>
     OP.value Nothing
     )
 
@@ -243,7 +243,7 @@ parseContributors = OP.option (OP.eitherReader readContributorString) (
     OP.long "newContributors" <>
     OP.metavar "DSL" <>
     OP.help "Contributors to add to the POSEIDON.yml file \
-            \ in the form \"[Firstname Lastname](Email address);...\"."
+            \ in the form \"[Firstname Lastname](Email address)<ORCID>;...\". The ORCIDs are optional."
     )
 
 readContributorString :: String -> Either String [ContributorSpec]
diff --git a/src/Poseidon/Core/Contributor.hs b/src/Poseidon/Core/Contributor.hs
index 02f3a673..89636a3b 100644
--- a/src/Poseidon/Core/Contributor.hs
+++ b/src/Poseidon/Core/Contributor.hs
@@ -44,14 +44,14 @@ instance ToJSON ContributorSpec where
         ]
 
 contributorSpecParser :: P.Parser [ContributorSpec]
-contributorSpecParser = P.try (P.sepBy oneContributorSpecParser (P.char ';' <* P.spaces))
+contributorSpecParser = P.try (P.sepBy oneContributorSpecParser (P.char ';' <* P.spaces)) <* P.spaces <* P.eof
 
 oneContributorSpecParser :: P.Parser ContributorSpec
 oneContributorSpecParser = do
     name <- P.between (P.char '[') (P.char ']') (P.manyTill P.anyChar (P.lookAhead (P.char ']')))
     email <- P.between (P.char '(') (P.char ')') (P.manyTill P.anyChar (P.lookAhead (P.char ')')))
-    -- TODO: add option to add ORCID here
-    return (ContributorSpec name email Nothing)
+    orcid <- P.optionMaybe $ P.between (P.char '<') (P.char '>') parseORCID
+    return (ContributorSpec name email orcid)
 
 -- | A data type to represent an ORCID
 -- see https://support.orcid.org/hc/en-us/articles/360006897674-Structure-of-the-ORCID-Identifier
@@ -62,7 +62,7 @@ data ORCID = ORCID
     deriving (Show, Eq, Ord)
 
 instance FromJSON ORCID where
-    parseJSON (String s) = case P.runParser parseORCID () "" (unpack s) of
+    parseJSON (String s) = case P.runParser (parseORCID <* P.eof) () "" (unpack s) of
         Left err -> fail $ showParsecErr err
         Right x  -> pure x
     parseJSON _          = mzero
@@ -76,7 +76,7 @@ parseORCID = do
             fourBlock <* m
         <*> fourBlock <* m
         <*> fourBlock <* m
-        <*> threeBlock <*> checksumDigit <* P.eof
+        <*> threeBlock <*> checksumDigit
     guard (validateORCID orcid) P.<?> "ORCID is not valid"
     return orcid
   where
diff --git a/test/Poseidon/Core/ContributorSpec.hs b/test/Poseidon/Core/ContributorSpec.hs
new file mode 100644
index 00000000..706577f5
--- /dev/null
+++ b/test/Poseidon/Core/ContributorSpec.hs
@@ -0,0 +1,37 @@
+{-# LANGUAGE OverloadedStrings #-}
+
+module Poseidon.Core.ContributorSpec (spec) where
+
+import           Poseidon.Core.Contributor
+
+import           Data.Either               (isLeft)
+import           Test.Hspec
+import qualified Text.Parsec               as P
+import           Text.Parsec.Error         (Message (..), newErrorMessage)
+import           Text.Parsec.Pos           (newPos)
+
+spec :: Spec
+spec = do
+    testContributorSpecParser
+
+testContributorSpecParser :: Spec
+testContributorSpecParser =
+    describe "Poseidon.Core.Contributor.contributorSpecParser" $ do
+    it "should work for one individual" $ do
+        P.runParser contributorSpecParser () "" "[A B C](abc@hmail.com)" `shouldBe`
+            Right [ContributorSpec "A B C" "abc@hmail.com" Nothing]
+    it "should work for multiple individuals" $ do
+            P.runParser contributorSpecParser () "" "[A B C](abc@hmail.com);[D E F](def@hmail.com)" `shouldBe`
+                Right [ContributorSpec "A B C" "abc@hmail.com" Nothing,
+                       ContributorSpec "D E F" "def@hmail.com" Nothing]
+    it "should work with ORCIDs" $ do
+            P.runParser contributorSpecParser () ""
+                "[A B C](abc@hmail.com)<0000-0002-1825-0097>;[D E F](def@hmail.com)<0000-0003-3448-5715>" `shouldBe`
+                Right [ContributorSpec "A B C" "abc@hmail.com" (Just $ ORCID "000000021825009" '7'),
+                       ContributorSpec "D E F" "def@hmail.com" (Just $ ORCID "000000033448571" '5')]
+    it "should fail with wrong ORCIDs" $ do
+            P.runParser contributorSpecParser () "" "[A B C](abc@hmail.com)<0000-0003-3448-5716>;[D E F](def@hmail.com)" `shouldBe`
+                Left (newErrorMessage (Expect "ORCID is not valid") (newPos "" 1 43))
+    it "should fail with trailing garbage" $ do
+            P.runParser contributorSpecParser () "" "[A B C](abc@hmail.com)Test;[D E F](def@hmail.com)" `shouldSatisfy` isLeft
+            P.runParser contributorSpecParser () "" "[A B C](abc@hmail.com);[D E F](def@hmail.com)Test" `shouldSatisfy` isLeft

From 3f288f955efacd8b615c519449336607f6ee555d Mon Sep 17 00:00:00 2001
From: Clemens Schmid <nevromecs@gmail.com>
Date: Mon, 3 Aug 2026 12:26:57 +0200
Subject: [PATCH 06/11] better handling of additional columns for trident list;
 should fix #380

---
 src/Poseidon/CLI/Trident/List.hs                |   6 +++---
 src/Poseidon/CLI/Trident/Serve.hs               |   6 +++---
 src/Poseidon/Core/Package.hs                    |  15 ++++++++++-----
 src/Poseidon/Core/ServerClient.hs               |   3 ++-
 .../GoldenTestCheckSumFile.txt                  |   3 ++-
 .../forge/ForgePac20/ForgePac20.janno           |   6 +++---
 .../genoconvert/out_vcf/Schiffels_2016.vcf.gz   | Bin 495 -> 495 bytes
 .../GoldenTestData/list/list8                   |   3 +++
 .../GoldenTestsRunCommands.hs                   |   7 +++++++
 .../Schmid_2028_utf8/Schmid_2028.janno          |   6 +++---
 10 files changed, 36 insertions(+), 19 deletions(-)
 create mode 100644 test/PoseidonGoldenTests/GoldenTestData/list/list8

diff --git a/src/Poseidon/CLI/Trident/List.hs b/src/Poseidon/CLI/Trident/List.hs
index 8c34d4c3..287b065c 100644
--- a/src/Poseidon/CLI/Trident/List.hs
+++ b/src/Poseidon/CLI/Trident/List.hs
@@ -114,7 +114,7 @@ runList (ListOptions repoLocation listEntity rawOutput onlyLatest) = do
                     let addJannoColFlag = case addJannoColSpec of
                             AddColAll -> "&additionalJannoColumns=ALL"
                             AddColList [] -> ""
-                            AddColList moreJannoColumns -> "&additionalJannoColumns=" ++ intercalate "," moreJannoColumns
+                            AddColList moreJannoColumns -> "&additionalJannoColumns=" ++ T.unpack (T.intercalate "," moreJannoColumns)
                     apiReturn <- processApiResponse (remoteURL ++ "/individuals" ++ qDefault archive ++ addJannoColFlag) False
                     case apiReturn of
                         ApiReturnExtIndividualInfo indInfo -> return indInfo
@@ -153,7 +153,7 @@ runList (ListOptions repoLocation listEntity rawOutput onlyLatest) = do
                     let addJannoColFlag = case addColSpec of
                             AddColAll -> "&additionalBibColumns=ALL"
                             AddColList [] -> ""
-                            AddColList moreBibFields -> "&additionalBibColumns=" ++ intercalate "," moreBibFields
+                            AddColList moreBibFields -> "&additionalBibColumns=" ++ T.unpack (T.intercalate "," moreBibFields)
                     apiReturn <- processApiResponse (remoteURL ++ "/bibliography" ++ qDefault archive ++ addJannoColFlag) False
                     case apiReturn of
                         ApiReturnBibInfo bibInfo -> return bibInfo
@@ -164,7 +164,7 @@ runList (ListOptions repoLocation listEntity rawOutput onlyLatest) = do
 
             let addBibFieldNames = case addColSpec of
                     AddColAll -> nub . concatMap (map fst . bibInfoAddCols) $ bibInfos
-                    AddColList names -> names
+                    AddColList names -> map T.unpack names
 
             -- warning in case the additional Columns do not exist in the entire janno dataset,
             -- we only output this warning if the columns were requested explicitly. Not if
diff --git a/src/Poseidon/CLI/Trident/Serve.hs b/src/Poseidon/CLI/Trident/Serve.hs
index 120e747e..af55782e 100644
--- a/src/Poseidon/CLI/Trident/Serve.hs
+++ b/src/Poseidon/CLI/Trident/Serve.hs
@@ -33,9 +33,9 @@ import           Control.Monad                  (forM)
 import           Control.Monad.IO.Class         (MonadIO, liftIO)
 import           Data.Coerce                    (coerce)
 import           Data.List                      (groupBy, intercalate, sortOn)
-import           Data.List.Split                (splitOn)
 import           Data.Maybe                     (isJust)
 import           Data.Scientific                (toRealFloat)
+import qualified Data.Text                      as T
 import           Data.Text.Lazy                 (pack)
 import           Data.Time                      (Day)
 import           Data.Version                   (Version, parseVersion,
@@ -227,7 +227,7 @@ runServer (ServeOptions archBaseDirs port ignoreChecksums certFiles) serverReady
             indInfo <- case maybeAdditionalColumnsString of
                     Just "ALL" -> getExtendedIndividualInfo pacs AddColAll -- Nothing means all Janno Columns
                     Just additionalColumnsString ->
-                        let additionalColumnNames = splitOn "," additionalColumnsString
+                        let additionalColumnNames = T.splitOn "," additionalColumnsString
                         in  getExtendedIndividualInfo pacs (AddColList additionalColumnNames)
                     Nothing -> getExtendedIndividualInfo pacs (AddColList [])
             let retData = ApiReturnExtIndividualInfo indInfo
@@ -241,7 +241,7 @@ runServer (ServeOptions archBaseDirs port ignoreChecksums certFiles) serverReady
             bibInfo <- case maybeAdditionalBibFieldsString of
                     Just "ALL" -> getBibliographyInfo pacs AddColAll -- Nothing means all Janno Columns
                     Just additionalBibFieldsString ->
-                        let additionalBibFields = splitOn "," additionalBibFieldsString
+                        let additionalBibFields = T.splitOn "," additionalBibFieldsString
                         in  getBibliographyInfo pacs (AddColList additionalBibFields)
                     Nothing -> getBibliographyInfo pacs (AddColList [])
             let retData = ApiReturnBibInfo bibInfo
diff --git a/src/Poseidon/Core/Package.hs b/src/Poseidon/Core/Package.hs
index eac95537..dd71cab1 100644
--- a/src/Poseidon/Core/Package.hs
+++ b/src/Poseidon/Core/Package.hs
@@ -111,7 +111,8 @@ import           Data.List                      (elemIndex, group, groupBy,
                                                  (\\))
 import           Data.Maybe                     (catMaybes, fromMaybe,
                                                  isNothing, mapMaybe)
-import           Data.Text                      (unpack)
+import qualified Data.Text                      as T
+import qualified Data.Text.Encoding             as TE
 import           Data.Time                      (Day, UTCTime (..),
                                                  getCurrentTime)
 import qualified Data.Vector                    as V
@@ -1012,10 +1013,14 @@ getExtendedIndividualInfo allPackages addJannoColSpec = sequence $ do -- list mo
     let name = show $ jPoseidonID jannoRow
         groups = map show $ getListColumn . jGroupName $ jannoRow
         colNames = case addJannoColSpec of
-            AddColAll    -> jannoHeaderString \\ ["Poseidon_ID", "Group_Name"] -- Nothing means all Janno columns
+            AddColAll    -> map T.pack jannoHeaderString \\ ["Poseidon_ID", "Group_Name"] -- Nothing means all Janno columns
                                                                           -- except for these two which are already explicit
             AddColList c -> c
-        additionalColumnEntries = [(k, Bchs.unpack <$> toNamedRecord jannoRow HM.!? Bchs.pack k) | k <- colNames]
+        -- additionalColumnEntries = [(k, Bchs.unpack <$> toNamedRecord jannoRow HM.!? Bchs.pack k) | k <- colNames]
+        additionalColumnEntries = [
+              (T.unpack k, T.unpack . TE.decodeUtf8 <$> HM.lookup (TE.encodeUtf8 k) (toNamedRecord jannoRow))
+            | k <- colNames
+            ]
     isLatest <- isLatestInCollection allPackages pac -- this lives in monad m
     -- double-return for m and then list.
     return . return $ ExtendedIndividualInfo name groups (makePacNameAndVersion pac) isLatest additionalColumnEntries
@@ -1038,14 +1043,14 @@ getBibliographyInfo allPackages addColSpec = do
                 jannoRow <- jointJanno
                 let bibKeys = case jPublication jannoRow of
                         Nothing -> []
-                        Just jannoPubList -> map (\(JannoPublication p) -> unpack p) $ getListColumn jannoPubList
+                        Just jannoPubList -> map (\(JannoPublication p) -> T.unpack p) $ getListColumn jannoPubList
                 True <- return $ bibId `elem` bibKeys
                 return ()
         let addBibEntries = case addColSpec of
                 -- with "all" we include all existing additional bib-entries except for the canonical ones that we anyway look up.
                 AddColAll -> [(k, Just v) | (k, v) <- bibFields, k `notElem` ["title", "author", "year", "journal", "doi"]]
                 -- with a selecton of colNames we just query the bib-fields for those exact fields.
-                AddColList colNames -> [(colName, colName `lookup` bibFields) | colName <- colNames]
+                AddColList colNames -> [(T.unpack colName, T.unpack colName `lookup` bibFields) | colName <- colNames]
         return $ BibliographyInfo nrSamples bibId ("title" `lookup` bibFields)
             ("author" `lookup` bibFields) ("year" `lookup` bibFields) ("journal" `lookup` bibFields)
             ("doi" `lookup` bibFields) addBibEntries
diff --git a/src/Poseidon/Core/ServerClient.hs b/src/Poseidon/Core/ServerClient.hs
index 0de2729b..0f7e83e3 100644
--- a/src/Poseidon/Core/ServerClient.hs
+++ b/src/Poseidon/Core/ServerClient.hs
@@ -31,6 +31,7 @@ import           Data.Aeson                (FromJSON, ToJSON (..), Value (..),
                                             toJSON, withObject, (.:), (.:?),
                                             (.=))
 import qualified Data.Aeson.KeyMap         (filter)
+import qualified Data.Text                 as T
 import           Data.Time                 (Day)
 import           Data.Version              (Version, showVersion)
 import           Network.HTTP.Conduit      (simpleHttp)
@@ -259,7 +260,7 @@ extIndInfo2IndInfoCollection extIndInfos =
     in  (indInfos, areLatest)
 
 -- type needed to specify additional Janno Columns to be queried from packages
-data AddColSpec = AddColList [String] | AddColAll
+data AddColSpec = AddColList [T.Text] | AddColAll
 
 data BibliographyInfo = BibliographyInfo {
     bibInfoNrSamples :: Int,
diff --git a/test/PoseidonGoldenTests/GoldenTestCheckSumFile.txt b/test/PoseidonGoldenTests/GoldenTestCheckSumFile.txt
index 4fc2ff38..73dff3db 100644
--- a/test/PoseidonGoldenTests/GoldenTestCheckSumFile.txt
+++ b/test/PoseidonGoldenTests/GoldenTestCheckSumFile.txt
@@ -34,6 +34,7 @@ d6eafec9087c88ed6a95e4a22f1f306c list list/list3
 bc636b9c03ea9359acd254a9911e5af3 list list/list5
 32c841b67d2995cdc1312f3721df5916 list list/list6
 35689d85d4ac5da9a4189b728403f16b list list/list7
+848800d4b2604248f2e606a2f192994a list list/list8
 b197fb8dd883c7469a4791e4a677f1c0 summarise summarise/summarise1
 d9e4b3f15d4e129a365d2064198d95b6 summarise summarise/summarise2
 5a5ff1b07bcc6ba917d5e492b886b71c survey survey/survey1
@@ -132,7 +133,7 @@ ad7e56177aad0a720f0bde13d47f2ac1 forge forge/ForgePac19/CHANGELOG.md
 9b22cab26cdae87bd79d24c289e48433 forge forge/ForgePac19/ForgePac19.fam
 504775c8994e25615b7662fc0495ff12 forge forge/ForgePac19/ForgePac19.janno
 3288b6ff2d7b02eec0f34a8434e4b7e3 forge forge/ForgePac20/POSEIDON.yml
-100405d0cc3bf72c1c3d7b87b7a22029 forge forge/ForgePac20/ForgePac20.janno
+589e62622e1ee6f0ad6268935dd540ba forge forge/ForgePac20/ForgePac20.janno
 ef1646043331ed9d67e4072ee46eb9f4 forge forge/ForgePac21/POSEIDON.yml
 8b8e1852b1e3cdd0ab0176dddce13bba forge forge/ForgePac21/ForgePac21.vcf
 848cf0fab32e4078a88cc17ad8ec3381 forge forge/ForgePac21/ForgePac21.janno
diff --git a/test/PoseidonGoldenTests/GoldenTestData/forge/ForgePac20/ForgePac20.janno b/test/PoseidonGoldenTests/GoldenTestData/forge/ForgePac20/ForgePac20.janno
index 82bfc4a0..8849f1c3 100644
--- a/test/PoseidonGoldenTests/GoldenTestData/forge/ForgePac20/ForgePac20.janno
+++ b/test/PoseidonGoldenTests/GoldenTestData/forge/ForgePac20/ForgePac20.janno
@@ -1,3 +1,3 @@
-Poseidon_ID	Genetic_Sex	Group_Name	Individual_ID	Species	Alternative_IDs	Alternative_IDs_Context	Relation_To	Relation_Degree	Relation_Type	Collection_ID	Custodian_Institution	Cultural_Era	Cultural_Era_URL	Archaeological_Culture	Archaeological_Culture_URL	Country	Country_ISO	Location	Site	Latitude	Longitude	Date_Type	Date_C14_Labnr	Date_C14_Uncal_BP	Date_C14_Uncal_BP_Err	Date_BC_AD_Start	Date_BC_AD_Median	Date_BC_AD_Stop	Chromosomal_Anomalies	MT_Haplogroup	Y_Haplogroup	Source_Material	Nr_Libraries	Library_Names	Capture_Type	UDG	Library_Built	Genotype_Ploidy	Data_Preparation_Pipeline_URL	Endogenous	Nr_SNPs	Coverage_on_Target_SNPs	Damage	Contamination	Contamination_Err	Contamination_Meas	Genetic_Source_Accession_IDs	Primary_Contact	Publication	Note	Keywords
-XXX001	F	POP1	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	testà	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	9	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a
-XXX002	F	POP2	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	MAMS-47224	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	9	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a
+Poseidon_ID	Genetic_Sex	Group_Name	Individual_ID	Species	Alternative_IDs	Alternative_IDs_Context	Relation_To	Relation_Degree	Relation_Type	Collection_ID	Custodian_Institution	Cultural_Era	Cultural_Era_URL	Archaeological_Culture	Archaeological_Culture_URL	Country	Country_ISO	Location	Site	Latitude	Longitude	Date_Type	Date_C14_Labnr	Date_C14_Uncal_BP	Date_C14_Uncal_BP_Err	Date_BC_AD_Start	Date_BC_AD_Median	Date_BC_AD_Stop	Chromosomal_Anomalies	MT_Haplogroup	Y_Haplogroup	Source_Material	Nr_Libraries	Library_Names	Capture_Type	UDG	Library_Built	Genotype_Ploidy	Data_Preparation_Pipeline_URL	Endogenous	Nr_SNPs	Coverage_on_Target_SNPs	Damage	Contamination	Contamination_Err	Contamination_Meas	Genetic_Source_Accession_IDs	Primary_Contact	Publication	Note	Keywords	起司蛋糕
+XXX001	F	POP1	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	testà	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	9	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	鑽頭
+XXX002	F	POP2	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	MAMS-47224	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	9	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	n/a	香腸沙拉
diff --git a/test/PoseidonGoldenTests/GoldenTestData/genoconvert/out_vcf/Schiffels_2016.vcf.gz b/test/PoseidonGoldenTests/GoldenTestData/genoconvert/out_vcf/Schiffels_2016.vcf.gz
index 8ef6ceacaf50e2f842f13701643f8c56561955a1..4d23fd675770b8d15a4695cb0866463ccc5a8c9b 100644
GIT binary patch
delta 404
zcmV;F0c-y61MdTnWq$@@=TzjkYn&w)Ub@?03#yoyDmf;v>F=&S&of@7hq&aw-L>kg
z-63Z2#&Y8a?&sy)-Gu7qcKO8%7u4v_mAlKV;wN6Hb6y^b^jf8P=04#oN`6$r<Z^xG
zrSdba&dNNglBX{M=Py^$^R5AwCY8^wcv&jdImr~0eyR~=i+?yLcdoqjAz%;z|3n14
zwHGyrMf6ZsDB7HzWbA@xc_lXM!?UluU`@6`NS1T5d-jR9ipaO`-ilx_Qg@8t7s!6U
zrxZ{aijHESm?##?6vaky8UZ>2GBufLSp?$NEQm)mvh~7{Y(f_(Sww_RD1iy|4*Ko|
z%{CYXUC>$+34h)YtyXzRYc<UQ%Als9k+V59>@kiu(Yld3(Hz6EOhdq0<Ml*)D~Nt9
zPNFda6zr*JHH+Vz%yY0(=v0N_ptIKc24|SM4h;_7&^`ReK%VWGCh{8B8xN0Q&xS4n
y<5>XW=csY$A~G9{2U6KGuk9XC+tQ~suXR0F`!U|*KMm77kNyI}3;8YE1ONa>q{)*2

delta 404
zcmV;F0c-y61MdTnWq(G+&Z)?6*EmZqymYt07F01YRdP&T)8Acvo@cyD4{^zVyKB`~
zyF<+4jpfD<+|SFoy9w3J?edEkE~wF;D|eS!#ZSCY=e#@=>9tDp%zeUFl>DfK$>sXW
zOXX);ot1e~B~M=j&R?#g=UoFVO)8&V@v>B^bCM}0{Zu2$7JqS0?p%54L%<*c{)q^7
zYcFaLi|C=OP_#Ka$=C(Y@=9#hhi6}R!J2G?kSyn9_v{mI6_Ib>y%oV=r0y8OFOdCy
zPbr`<6dlDtF;Og(DT<BaGy-%4WNI?gvIxYjSrCtCWb1_?*@P}ovWN(sPy!R^9rWD`
znr$!&x}dct5`VlQTCMVs)@qsqltE2HBWH7J*kc@RqIDy6qB(|RnTCM1#_NgpRuKJI
zoJ3;;DA-fcY8Jmande}o(5VW;L1(S?4bCui9U2_Ep?mm`fjrwWP2@GMHy$3ro()|D
y#<Kv#&r##hMPxP@52UhXUfVsOwxv&NUh8_U_G7%qe+{O29{mM9;pf)d1ONcfI>p-n

diff --git a/test/PoseidonGoldenTests/GoldenTestData/list/list8 b/test/PoseidonGoldenTests/GoldenTestData/list/list8
new file mode 100644
index 00000000..aa1c56bd
--- /dev/null
+++ b/test/PoseidonGoldenTests/GoldenTestData/list/list8
@@ -0,0 +1,3 @@
+Individual	Group	Package	PackageVersion	Is Latest	起司蛋糕
+XXX001	POP1	Schmid_2028	1.0.0	True	鑽頭
+XXX002	POP2	Schmid_2028	1.0.0	True	香腸沙拉
diff --git a/test/PoseidonGoldenTests/GoldenTestsRunCommands.hs b/test/PoseidonGoldenTests/GoldenTestsRunCommands.hs
index a500711b..73257093 100644
--- a/test/PoseidonGoldenTests/GoldenTestsRunCommands.hs
+++ b/test/PoseidonGoldenTests/GoldenTestsRunCommands.hs
@@ -457,6 +457,13 @@ testPipelineList testDir checkFilePath = do
         }
     runAndChecksumStdOut checkFilePath testDir (testLog $ runList listOpts7) "list" 7
 
+    let listOpts8 = listOpts1 {
+          _listRepoLocation  = RepoLocal [testPacsDirOther </> "Schmid_2028_utf8"]
+        , _listListEntity    = ListIndividuals (AddColList ["起司蛋糕"])
+        , _listRawOutput     = True
+        }
+    runAndChecksumStdOut checkFilePath testDir (testLog $ runList listOpts8) "list" 8
+
 
 testPipelineSummarise :: FilePath -> FilePath -> IO ()
 testPipelineSummarise testDir checkFilePath = do
diff --git a/test/testDat/testPackages/other_test_packages/Schmid_2028_utf8/Schmid_2028.janno b/test/testDat/testPackages/other_test_packages/Schmid_2028_utf8/Schmid_2028.janno
index 2c26f32d..e439d8dc 100755
--- a/test/testDat/testPackages/other_test_packages/Schmid_2028_utf8/Schmid_2028.janno
+++ b/test/testDat/testPackages/other_test_packages/Schmid_2028_utf8/Schmid_2028.janno
@@ -1,3 +1,3 @@
-Poseidon_ID	Group_Name	Genetic_Sex	Date_C14_Labnr
-XXX001	POP1	F	testà
-XXX002	POP2	F	MAMS-47224 
+Poseidon_ID	Group_Name	Genetic_Sex	Date_C14_Labnr	起司蛋糕
+XXX001	POP1	F	testà	鑽頭
+XXX002	POP2	F	MAMS-47224	香腸沙拉

From 9c3ddf8b89d4638c519c693856d9728188663ed2 Mon Sep 17 00:00:00 2001
From: Clemens Schmid <nevromecs@gmail.com>
Date: Mon, 3 Aug 2026 14:37:21 +0200
Subject: [PATCH 07/11] another test to make sure the remote list behaviour
 described in #380 is also fixed, not just the local case

---
 test/PoseidonGoldenTests/GoldenTestCheckSumFile.txt |  1 +
 .../GoldenTestData/listRemote/listRemote6           |  3 +++
 test/PoseidonGoldenTests/GoldenTestsRunCommands.hs  | 13 ++++++++++++-
 3 files changed, 16 insertions(+), 1 deletion(-)
 create mode 100644 test/PoseidonGoldenTests/GoldenTestData/listRemote/listRemote6

diff --git a/test/PoseidonGoldenTests/GoldenTestCheckSumFile.txt b/test/PoseidonGoldenTests/GoldenTestCheckSumFile.txt
index 73dff3db..e43036b7 100644
--- a/test/PoseidonGoldenTests/GoldenTestCheckSumFile.txt
+++ b/test/PoseidonGoldenTests/GoldenTestCheckSumFile.txt
@@ -161,6 +161,7 @@ b43da4d5734371c0648553120f812466 fetch fetch/multi_packages_2/Lamnidis_2018-1.0.
 ed1d1343a7ff26274690c530a03cd070 listRemote listRemote/listRemote3
 0433b2a80ee5a2eb5bf8c6404130e562 listRemote listRemote/listRemote4
 e8be7325d86f75c8df826f91421e0239 listRemote listRemote/listRemote5
+848800d4b2604248f2e606a2f192994a listRemote listRemote/listRemote6
 3ea2b421436a1be5cb631eaf6aa39546 jannocoalesce jannocoalesce/target1.janno
 e429b08154988f73c502921beb7b0842 jannocoalesce jannocoalesce/target2.janno
 a7983b6a2537513c43e5dc8105f6cec9 jannocoalesce jannocoalesce/target3.janno
\ No newline at end of file
diff --git a/test/PoseidonGoldenTests/GoldenTestData/listRemote/listRemote6 b/test/PoseidonGoldenTests/GoldenTestData/listRemote/listRemote6
new file mode 100644
index 00000000..aa1c56bd
--- /dev/null
+++ b/test/PoseidonGoldenTests/GoldenTestData/listRemote/listRemote6
@@ -0,0 +1,3 @@
+Individual	Group	Package	PackageVersion	Is Latest	起司蛋糕
+XXX001	POP1	Schmid_2028	1.0.0	True	鑽頭
+XXX002	POP2	Schmid_2028	1.0.0	True	香腸沙拉
diff --git a/test/PoseidonGoldenTests/GoldenTestsRunCommands.hs b/test/PoseidonGoldenTests/GoldenTestsRunCommands.hs
index 73257093..8ba872f1 100644
--- a/test/PoseidonGoldenTests/GoldenTestsRunCommands.hs
+++ b/test/PoseidonGoldenTests/GoldenTestsRunCommands.hs
@@ -456,7 +456,7 @@ testPipelineList testDir checkFilePath = do
             _listListEntity = ListBibliography AddColAll
         }
     runAndChecksumStdOut checkFilePath testDir (testLog $ runList listOpts7) "list" 7
-
+    
     let listOpts8 = listOpts1 {
           _listRepoLocation  = RepoLocal [testPacsDirOther </> "Schmid_2028_utf8"]
         , _listListEntity    = ListIndividuals (AddColList ["起司蛋糕"])
@@ -1365,6 +1365,9 @@ archives = Left $ ArchiveConfig [
         "test/testDat/testPackages/ancient/Schiffels_2016"
       , "test/testDat/testPackages/ancient/Schmid_2028"
       ] Nothing Nothing Nothing [] Nothing
+    , ArchiveSpec "testArchive3" [
+        "test/testDat/testPackages/other_test_packages/Schmid_2028_utf8"
+      ] Nothing Nothing Nothing [] Nothing
     ]
 
  -- Note: We here use our test server (no SSL and different port). The reason is that
@@ -1505,6 +1508,14 @@ testPipelineListRemote testDir checkFilePath = do
             , _listRawOutput     = True
             }
         runAndChecksumStdOut checkFilePath testDir (testLog $ runList listOpts5) "listRemote" 5
+        
+        -- list with non-ascii unicode characters
+        let listOpts6 = listOpts1 {
+              _listRepoLocation = RepoRemote (ArchiveEndpoint "http://localhost:3001" (Just "testArchive3"))
+            , _listListEntity   = ListIndividuals (AddColList ["起司蛋糕"])
+            , _listRawOutput    = True
+            }
+        runAndChecksumStdOut checkFilePath testDir (testLog $ runList listOpts6) "listRemote" 6
         ) (
         killThread threadID
         )

From d261cd94217539d8ad728a4ed7a3a492879cc7b4 Mon Sep 17 00:00:00 2001
From: Clemens Schmid <nevromecs@gmail.com>
Date: Mon, 3 Aug 2026 14:41:29 +0200
Subject: [PATCH 08/11] stylish-haskell

---
 test/PoseidonGoldenTests/GoldenTestsRunCommands.hs | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/test/PoseidonGoldenTests/GoldenTestsRunCommands.hs b/test/PoseidonGoldenTests/GoldenTestsRunCommands.hs
index 8ba872f1..ab2aaec0 100644
--- a/test/PoseidonGoldenTests/GoldenTestsRunCommands.hs
+++ b/test/PoseidonGoldenTests/GoldenTestsRunCommands.hs
@@ -456,7 +456,7 @@ testPipelineList testDir checkFilePath = do
             _listListEntity = ListBibliography AddColAll
         }
     runAndChecksumStdOut checkFilePath testDir (testLog $ runList listOpts7) "list" 7
-    
+
     let listOpts8 = listOpts1 {
           _listRepoLocation  = RepoLocal [testPacsDirOther </> "Schmid_2028_utf8"]
         , _listListEntity    = ListIndividuals (AddColList ["起司蛋糕"])
@@ -1508,7 +1508,7 @@ testPipelineListRemote testDir checkFilePath = do
             , _listRawOutput     = True
             }
         runAndChecksumStdOut checkFilePath testDir (testLog $ runList listOpts5) "listRemote" 5
-        
+
         -- list with non-ascii unicode characters
         let listOpts6 = listOpts1 {
               _listRepoLocation = RepoRemote (ArchiveEndpoint "http://localhost:3001" (Just "testArchive3"))

From 345ef603047070a1089d6935cf2488d670b4ac8f Mon Sep 17 00:00:00 2001
From: Clemens Schmid <clemens@nevrome.de>
Date: Sun, 9 Aug 2026 12:31:11 +0200
Subject: [PATCH 09/11] update of changelog

---
 CHANGELOG.md | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 5008d888..904efc84 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,3 +1,9 @@
+- V 2.2.1.0:
+    - Made the display of description and source url in the explorer page of the of the server's html API indendent of each other.
+    - Made the source column hide when the necessary URL is missing on the archive page.
+    - Added a input validation feature that checks line endings of the first (!) row in text files in packages.
+    - Made it possible to give ORCIDs with `--newContributors` in rectify.
+    - Fixed encoding issues in `trident list` when additional .janno columns are requested.
 - V 2.2.0.1:
     - By default only show the first five samples on the package page of the server's html API.
 - V 2.2.0.0:

From 0de9ddb5a8c4ee82d6254e1a5040f77014735f3c Mon Sep 17 00:00:00 2001
From: Clemens Schmid <clemens@nevrome.de>
Date: Sun, 9 Aug 2026 15:26:14 +0200
Subject: [PATCH 10/11] calling checkfile in validate for nicer error messages
 with wrong file paths

---
 CHANGELOG.md                         |  3 +-
 src/Poseidon/CLI/Trident/Validate.hs |  9 +++-
 src/Poseidon/Core/Package.hs         | 64 +++++++++++++---------------
 3 files changed, 40 insertions(+), 36 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 904efc84..915fa221 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,9 +1,10 @@
 - V 2.2.1.0:
     - Made the display of description and source url in the explorer page of the of the server's html API indendent of each other.
     - Made the source column hide when the necessary URL is missing on the archive page.
-    - Added a input validation feature that checks line endings of the first (!) row in text files in packages.
+    - Added a input validation feature that checks line endings of the first (!) row in text files in packages. Only runs when checksums are present, because only then a difference in line endings can lead to unexpected behaviour.
     - Made it possible to give ORCIDs with `--newContributors` in rectify.
     - Fixed encoding issues in `trident list` when additional .janno columns are requested.
+    - Nicer error messages in case of missing input files in `validate`.
 - V 2.2.0.1:
     - By default only show the first five samples on the package page of the server's html API.
 - V 2.2.0.0:
diff --git a/src/Poseidon/CLI/Trident/Validate.hs b/src/Poseidon/CLI/Trident/Validate.hs
index ebf87e11..44bc120e 100644
--- a/src/Poseidon/CLI/Trident/Validate.hs
+++ b/src/Poseidon/CLI/Trident/Validate.hs
@@ -10,6 +10,7 @@ import           Poseidon.Core.Janno            (JannoRows (..), readJannoFile)
 import           Poseidon.Core.Package          (PackageReadOptions (..),
                                                  PoseidonException (..),
                                                  PoseidonYamlStruct (..),
+                                                 checkGenoFiles,
                                                  defaultPackageReadOptions,
                                                  getJointIndividualInfo,
                                                  makePseudoPackageFromGenotypeData,
@@ -17,7 +18,8 @@ import           Poseidon.Core.Package          (PackageReadOptions (..),
                                                  validateForge, validateGeno)
 import           Poseidon.Core.SequencingSource (SeqSourceRows (..),
                                                  readSeqSourceFile)
-import           Poseidon.Core.Utils            (PoseidonIO, logError, logInfo)
+import           Poseidon.Core.Utils            (PoseidonIO, checkFile,
+                                                 logError, logInfo)
 
 import           Control.Monad                  (forM_, unless, when)
 import           Control.Monad.Catch            (throwM)
@@ -96,6 +98,7 @@ runValidate (ValidateOptions
     conclude (not packagesSkipped) noExitCode
 runValidate (ValidateOptions (ValPlanPoseidonYaml path) _ _ noExitCode _) = do
     logInfo $ "Validating: " ++ path
+    checkFile path Nothing
     bs <- liftIO $ B.readFile path
     yml <- case decodeEither' bs of
         Left err  -> throwM $ PoseidonYamlParseException path err
@@ -108,21 +111,25 @@ runValidate (ValidateOptions (ValPlanGeno geno) _ _ noExitCode _) = do
             GenotypePlink      gf _ _ _ _ _ -> gf
             GenotypeVCF        gf _         -> gf
     logInfo $ "Validating: " ++ gFile
+    checkGenoFiles True "" (genotypeFileSpec geno)
     pac <- makePseudoPackageFromGenotypeData geno
     validateGeno pac True
     conclude True noExitCode
 runValidate (ValidateOptions (ValPlanJanno (VersionedFile pv path)) mandatoryJannoCols _ noExitCode _) = do
     logInfo $ "Validating: " ++ path
+    checkFile path Nothing
     (_,JannoRows entries) <- readJannoFile pv mandatoryJannoCols path
     logInfo $ "All " ++ show (length entries) ++ " entries are valid"
     conclude True noExitCode
 runValidate (ValidateOptions (ValPlanSSF (VersionedFile pv path)) _ mandatorySSFCols noExitCode _) = do
     logInfo $ "Validating: " ++ path
+    checkFile path Nothing
     (SeqSourceRows entries) <- readSeqSourceFile pv mandatorySSFCols path
     logInfo $ "All " ++ show (length entries) ++ " entries are valid"
     conclude True noExitCode
 runValidate (ValidateOptions (ValPlanBib path) _ _ noExitCode _) = do
     logInfo $ "Validating: " ++ path
+    checkFile path Nothing
     entries <- liftIO $ readBibTeXFile path
     logInfo $ "All " ++ show (length entries) ++ " entries are valid"
     conclude True noExitCode
diff --git a/src/Poseidon/Core/Package.hs b/src/Poseidon/Core/Package.hs
index dd71cab1..467051c4 100644
--- a/src/Poseidon/Core/Package.hs
+++ b/src/Poseidon/Core/Package.hs
@@ -10,6 +10,7 @@ module Poseidon.Core.Package (
     LicenseSpec (..),
     findAllPoseidonYmlFiles,
     checkJannoIndConsistency,
+    checkGenoFiles,
     readPoseidonPackageCollection,
     readPoseidonPackageCollectionWithSkipIndicator,
     getJointGenotypeData,
@@ -591,40 +592,35 @@ checkFiles baseDir ignoreChecksums ignoreGenotypeFilesMissing yml = do
                        checkFile fn $ _posYamlSeqSourceFileChkSum yml
     -- Check Genotype files
     unless ignoreGenotypeFilesMissing $ do
-        let gd = _posYamlGenotypeData yml
-            d = baseDir
-        case genotypeFileSpec gd of
-            GenotypeEigenstrat genoF genoFc snpF snpFc indF indFc -> do
-                if ignoreChecksums
-                then do
-                    checkFile (d </> genoF) Nothing
-                    checkFile (d </> snpF)  Nothing
-                    checkFile (d </> indF)  Nothing
-                else do
-                    checkLineEndingIfNotZipped (d </> genoF)
-                    checkFile (d </> genoF) genoFc
-                    checkLineEndingIfNotZipped (d </> snpF)
-                    checkFile (d </> snpF)  snpFc
-                    checkLineEndingIfNotZipped (d </> indF)
-                    checkFile (d </> indF)  indFc
-            GenotypePlink genoF genoFc snpF snpFc indF indFc -> do
-                if ignoreChecksums
-                then do
-                    checkFile (d </> genoF) Nothing
-                    checkFile (d </> snpF)  Nothing
-                    checkFile (d </> indF)  Nothing
-                else do
-                    checkFile (d </> genoF) genoFc
-                    checkLineEndingIfNotZipped (d </> snpF)
-                    checkFile (d </> snpF)  snpFc
-                    checkLineEndingIfNotZipped (d </> indF)
-                    checkFile (d </> indF)  indFc
-            GenotypeVCF genoF genoFc -> do
-                if ignoreChecksums
-                then checkFile (d </> genoF) Nothing
-                else do
-                    checkLineEndingIfNotZipped (d </> genoF)
-                    checkFile (d </> genoF) genoFc
+        checkGenoFiles ignoreChecksums baseDir (genotypeFileSpec (_posYamlGenotypeData yml))
+
+checkGenoFiles :: Bool -> FilePath -> GenotypeFileSpec -> PoseidonIO ()
+checkGenoFiles True d (GenotypeEigenstrat genoF _ snpF _ indF _) = do
+    checkFile (d </> genoF) Nothing
+    checkFile (d </> snpF)  Nothing
+    checkFile (d </> indF)  Nothing
+checkGenoFiles False d (GenotypeEigenstrat genoF genoFc snpF snpFc indF indFc) = do
+    checkLineEndingIfNotZipped (d </> genoF)
+    checkFile (d </> genoF) genoFc
+    checkLineEndingIfNotZipped (d </> snpF)
+    checkFile (d </> snpF)  snpFc
+    checkLineEndingIfNotZipped (d </> indF)
+    checkFile (d </> indF)  indFc
+checkGenoFiles True d (GenotypePlink genoF _ snpF _ indF _) = do
+    checkFile (d </> genoF) Nothing
+    checkFile (d </> snpF)  Nothing
+    checkFile (d </> indF)  Nothing
+checkGenoFiles False d (GenotypePlink genoF genoFc snpF snpFc indF indFc) = do
+    checkFile (d </> genoF) genoFc
+    checkLineEndingIfNotZipped (d </> snpF)
+    checkFile (d </> snpF)  snpFc
+    checkLineEndingIfNotZipped (d </> indF)
+    checkFile (d </> indF)  indFc
+checkGenoFiles True d (GenotypeVCF genoF _) = do
+    checkFile (d </> genoF) Nothing
+checkGenoFiles False d (GenotypeVCF genoF genoFc) = do
+    checkLineEndingIfNotZipped (d </> genoF)
+    checkFile (d </> genoF) genoFc
 
 -- the last flag is important for reading VCFs, which can lack group and sex information.
 checkJannoIndConsistency :: String -> JannoRows -> [EigenstratIndEntry] -> Bool -> IO ()

From 38d4045f3b45b203736794fe014f1878cd555454 Mon Sep 17 00:00:00 2001
From: Clemens Schmid <nevromecs@gmail.com>
Date: Tue, 11 Aug 2026 13:30:45 +0200
Subject: [PATCH 11/11] version bump

---
 poseidon-hs.cabal | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/poseidon-hs.cabal b/poseidon-hs.cabal
index ae2c1040..ed185b9b 100644
--- a/poseidon-hs.cabal
+++ b/poseidon-hs.cabal
@@ -1,5 +1,5 @@
 name:                poseidon-hs
-version:             2.2.0.1
+version:             2.2.1.0
 synopsis:            A package with tools for working with Poseidon genotype data
 description:         The tools in this package read and analyse Poseidon-formatted genotype databases, a modular system for storing genotype data from thousands of individuals.
 license:             MIT