Allow separator to be overridden from command line

This also fixes that parsing separators on the command line and the
rules file was not handled the same way.

hledger-lib/Hledger/Read/Common.hs

@@ -50,6 +50,7 @@ module Hledger.Read.Common (
   getAccountAliases,
   clearAccountAliases,
   journalAddFile,
+  getSpecialSeparators,
 
   -- * parsers
   -- ** transaction bits
@@ -162,7 +163,7 @@ data InputOpts = InputOpts {
      mformat_           :: Maybe StorageFormat  -- ^ a file/storage format to try, unless overridden
                                                 --   by a filename prefix. Nothing means try all.
     ,mrules_file_       :: Maybe FilePath       -- ^ a conversion rules file to use (when reading CSV)
-    ,separator_         :: Char                 -- ^ the separator to use (when reading CSV)
+    ,separator_         :: Maybe Char           -- ^ the separator to use (when reading CSV)
     ,aliases_           :: [String]             -- ^ account name aliases to apply
     ,anon_              :: Bool                 -- ^ do light anonymisation/obfuscation of the data
     ,ignore_assertions_ :: Bool                 -- ^ don't check balance assertions
@@ -175,14 +176,14 @@ data InputOpts = InputOpts {
 instance Default InputOpts where def = definputopts
 
 definputopts :: InputOpts
-definputopts = InputOpts def def ',' def def def def True def def
+definputopts = InputOpts def def def def def def def True def def
 
 rawOptsToInputOpts :: RawOpts -> InputOpts
 rawOptsToInputOpts rawopts = InputOpts{
    -- files_             = listofstringopt "file" rawopts
    mformat_           = Nothing
   ,mrules_file_       = maybestringopt "rules-file" rawopts
-  ,separator_         = fromMaybe ',' (maybecharopt "separator" rawopts)
+  ,separator_         = maybestringopt "separator" rawopts >>= getSpecialSeparators
   ,aliases_           = listofstringopt "alias" rawopts
   ,anon_              = boolopt "anon" rawopts
   ,ignore_assertions_ = boolopt "ignore-assertions" rawopts
@@ -194,6 +195,14 @@ rawOptsToInputOpts rawopts = InputOpts{
 
 --- * parsing utilities
 
+-- | Parse special separator names TAB and SPACE, or return the first
+-- character. Return Nothing on empty string
+getSpecialSeparators :: String -> Maybe Char
+getSpecialSeparators "SPACE" = Just ' '
+getSpecialSeparators "TAB" = Just '\t'
+getSpecialSeparators (x:_) = Just x
+getSpecialSeparators [] = Nothing
+
 -- | Run a text parser in the identity monad. See also: parseWithState.
 runTextParser, rtp
   :: TextParser Identity a -> Text -> Either (ParseErrorBundle Text CustomErr) a

hledger-lib/Hledger/Read/CsvReader.hs

@@ -71,7 +71,7 @@ import Text.Printf (printf)
 
 import Hledger.Data
 import Hledger.Utils
-import Hledger.Read.Common (Reader(..),InputOpts(..),amountp, statusp, genericSourcePos, finaliseJournal)
+import Hledger.Read.Common (Reader(..),InputOpts(..),amountp, statusp, genericSourcePos, getSpecialSeparators, finaliseJournal)
 
 type CSV = [Record]
 
@@ -104,13 +104,13 @@ parse iopts f t = do
                 -- better preemptively reverse them once more. XXX inefficient
                 pj' = journalReverse pj
 
-getSeparatorFromRules :: Char -> CsvRules -> Char
+-- | Decide which separator to get.
-getSeparatorFromRules defaultSeparator rules =
+-- If the external separator is provided, take it. Otherwise, look at the rules. Finally, return ','.
-  maybe defaultSeparator id (getSeparator <$> getDirective "separator" rules)
+getSeparator :: Maybe Char -> CsvRules -> Char
-  where getSeparator :: String -> Char
+getSeparator externalSeparator rules = head $
-        getSeparator "SPACE" = ' '
+  catMaybes [ externalSeparator
-        getSeparator "TAB" = '\t'
+            , getDirective "separator" rules >>= getSpecialSeparators
-        getSeparator x = head x
+            , Just ',']
 
 -- | Read a Journal from the given CSV data (and filename, used for error
 -- messages), or return an error. Proceed as follows:
@@ -123,9 +123,9 @@ getSeparatorFromRules defaultSeparator rules =
 -- 4. if the rules file didn't exist, create it with the default rules and filename
 -- 5. return the transactions as a Journal
 -- @
-readJournalFromCsv :: Char -> Maybe FilePath -> FilePath -> Text -> IO (Either String Journal)
+readJournalFromCsv :: Maybe Char -> Maybe FilePath -> FilePath -> Text -> IO (Either String Journal)
 readJournalFromCsv _ Nothing "-" _ = return $ Left "please use --rules-file when reading CSV from stdin"
-readJournalFromCsv separator mrulesfile csvfile csvdata =
+readJournalFromCsv commandLineSeparator mrulesfile csvfile csvdata =
  handle (\(e::IOException) -> return $ Left $ show e) $ do
 
   -- make and throw an IO exception.. which we catch and convert to an Either above ?
@@ -156,7 +156,7 @@ readJournalFromCsv separator mrulesfile csvfile csvdata =
   records <- (either throwerr id .
               dbg2 "validateCsv" . validateCsv rules skiplines .
               dbg2 "parseCsv")
-             `fmap` parseCsv (getSeparatorFromRules separator rules) parsecfilename csvdata
+             `fmap` parseCsv (getSeparator commandLineSeparator rules) parsecfilename csvdata
   dbg1IO "first 3 csv records" $ take 3 records
 
   -- identify header lines

tests/csv.test

@@ -527,7 +527,7 @@ $  ./hledger-csv
 
 >=0
 
-# 25. specify alternative delimiter in rules
+# 25. specify alternative whitespace delimiter in rules
 <
 2009/10/01	Flubber Co	50	123
 
@@ -540,6 +540,39 @@ separator TAB
 $  ./hledger-csv
 2009/10/01 Flubber Co
     (assets:myacct)             $50 = $123
+
+>=0
+
+# 26. specify char delimiter in rules
+<
+2009/10/01;Flubber Co;50;123
+
+RULES
+fields date, description, amount, balance
+currency $
+account1 (assets:myacct)
+separator ;
+
+$  ./hledger-csv
+2009/10/01 Flubber Co
+    (assets:myacct)             $50 = $123
+
+>=0
+
+# 27. command line delimiter overrides configuration file
+<
+2009/10/01	Flubber Co	50	123
+
+RULES
+fields date, description, amount, balance
+currency $
+account1 (assets:myacct)
+separator ;
+
+$  ./hledger-csv --separator 'TAB'
+2009/10/01 Flubber Co
+    (assets:myacct)             $50 = $123
+
 >=0
 
 ## 25. A single unbalanced posting with number other than 1 also should not generate a balancing posting.