From 32eb839eac148a68ac50ed7aeb26e9bfe0754a42 Mon Sep 17 00:00:00 2001
From: Simon Michael <simon@joyful.com>
Date: Sat, 29 Feb 2020 09:11:56 -0800
Subject: [PATCH] timedot: rewrite the parser, making it more usable

Now, org headlines before the first day entry are ignored,
regardless of content.

Note, blank lines inside a day entry are not allowed, currently.

It's now easier to be both valid journal and valid timedot at the same
time, so guessing the format of stdin is unreliable, and some tests
are failing. See following commit.
---
 hledger-lib/Hledger/Read/TimedotReader.hs | 119 ++++++++++++++--------
 1 file changed, 79 insertions(+), 40 deletions(-)

diff --git a/hledger-lib/Hledger/Read/TimedotReader.hs b/hledger-lib/Hledger/Read/TimedotReader.hs
index de8924a7f..1a21a448d 100644
--- a/hledger-lib/Hledger/Read/TimedotReader.hs
+++ b/hledger-lib/Hledger/Read/TimedotReader.hs
@@ -51,14 +51,14 @@ import Control.Monad.Except (ExceptT)
 import Control.Monad.State.Strict
 import Data.Char (isSpace)
 import Data.List (foldl')
-import Data.Maybe
 import Data.Text (Text)
 import qualified Data.Text as T
+import Data.Time (Day)
 import Text.Megaparsec hiding (parse)
 import Text.Megaparsec.Char
 
 import Hledger.Data
-import Hledger.Read.Common
+import Hledger.Read.Common hiding (emptyorcommentlinep)
 import Hledger.Utils
 
 -- ** reader
@@ -73,37 +73,56 @@ reader = Reader
 
 -- | Parse and post-process a "Journal" from the timedot format, or give an error.
 parse :: InputOpts -> FilePath -> Text -> ExceptT String IO Journal
-parse = parseAndFinaliseJournal' timedotfilep
+parse = parseAndFinaliseJournal' timedotp
 
 -- ** utilities
 
-traceparse :: Monad m => a -> m a
-traceparse = return
--- traceparse :: String -> JournalParser m ()
--- traceparse = lift.traceParse
+traceparse :: String -> TextParser m ()
+traceparse = const $ return ()
+-- traceparse = traceParse  -- for debugging
 
 -- ** parsers
+{-
+Rough grammar for timedot format:
 
-timedotfilep :: JournalParser m ParsedJournal
-timedotfilep = do many timedotfileitemp
-                  eof
-                  get
+timedot:           preamble day*
+preamble:          (emptyline | commentline | orgheading)*
+orgheading:        orgheadingprefix restofline
+day:               dateline entry* (emptyline | commentline)*
+dateline:          orgheadingprefix? date description?
+orgheadingprefix:  star+ space+
+description:       restofline  ; till semicolon?
+entry:          orgheadingprefix? space* singlespaced (doublespace quantity?)?
+doublespace:       space space+
+quantity:          (dot (dot | space)* | number | number unit)
 
-timedotfileitemp :: JournalParser m ()
-timedotfileitemp = do
-  traceparse "timedotfileitemp"
-  choice [
-    try $ void $ lift emptyorcommentlinep'
-   ,try timedotdayp >>= \ts -> modify' (addTransactions ts)
-   ,lift $ skipSome anySingle >> eolof  -- an initial line not beginning with a date, ignore
-   ] <?> "timedot day entry, or default year or comment line or blank line"
+Date lines and item lines can begin with an org heading prefix, which is ignored.
+Org headings before the first date line are ignored, regardless of content.
+-}
 
-addTransactions :: [Transaction] -> Journal -> Journal
-addTransactions ts j = foldl' (flip ($)) j (map addTransaction ts)
+timedotfilep = timedotp -- XXX rename export above
 
-emptyorcommentlinep' = optional orgheadingprefixp >> emptyorcommentlinep
+timedotp :: JournalParser m ParsedJournal
+timedotp = preamblep >> many dayp >> eof >> get
 
-orgheadingprefixp = skipSome (char '*') >> skipSome spacenonewline
+preamblep :: JournalParser m ()
+preamblep = do
+  lift $ traceparse "preamblep"
+  void $ many $ notFollowedBy datelinep >> (lift $ emptyorcommentlinep "#;*")
+
+-- | XXX new comment line parser, move to Hledger.Read.Common.emptyorcommentlinep
+-- Parse empty lines, all-blank lines, and lines beginning with any of the provided
+-- comment-beginning characters.
+emptyorcommentlinep :: [Char] -> TextParser m ()
+emptyorcommentlinep cs =
+  label ("empty line or comment line beginning with "++cs) $ do
+    traceparse "emptyorcommentlinep" -- XXX possible to combine label and traceparse ?
+    skipMany spacenonewline
+    void newline <|> void commentp
+    where
+      commentp = do
+        choice (map (some.char) cs)
+        takeWhileP Nothing (/='\n') <* newline
 
 -- | Parse timedot day entries to zero or more time transactions for that day.
 -- @
@@ -112,30 +131,50 @@ orgheadingprefixp = skipSome (char '*') >> skipSome spacenonewline
 -- biz.research .
 -- inc.client1  .... .... .... .... .... ....
 -- @
-timedotdayp :: JournalParser m [Transaction]
-timedotdayp = do
-  traceparse " timedotdayp"
+dayp :: JournalParser m ()
+dayp = label "timedot day entry" $ do
+  lift $ traceparse "dayp"
+  (d,desc) <- datelinep
+  ts <- many entryp
+  let ts' = map (\t -> t{tdate=d, tdescription=desc}) ts
+  modify' $ addTransactions ts'
+  void $ many $
+    (lift $ emptyorcommentlinep "#;") <|> orgnondatelinep
+  where
+    addTransactions :: [Transaction] -> Journal -> Journal
+    addTransactions ts j = foldl' (flip ($)) j (map addTransaction ts)
+
+datelinep :: JournalParser m (Day,Text)
+datelinep = do
+  lift $ traceparse "datelinep"
   lift $ optional orgheadingprefixp
   d <- datep
-  daydesc <- strip <$> lift restofline
-  es <- catMaybes <$> many (const Nothing <$> try (lift emptyorcommentlinep') <|>
-                            Just <$> (notFollowedBy datep >> timedotentryp))
-  return $ map (\t -> t{tdate=d, tdescription=T.pack daydesc}) es -- <$> many timedotentryp
+  desc <- strip <$> lift restofline
+  return (d, T.pack desc)
+
+orgnondatelinep :: JournalParser m ()
+orgnondatelinep = do
+  lift $ traceparse "orgnondatelinep"
+  notFollowedBy datelinep
+  lift orgheadingprefixp
+  void $ lift restofline
+
+orgheadingprefixp = skipSome (char '*') >> skipSome spacenonewline
 
 -- | Parse a single timedot entry to one (dateless) transaction.
 -- @
 -- fos.haskell  .... ..
 -- @
-timedotentryp :: JournalParser m Transaction
-timedotentryp = do
-  traceparse "  timedotentryp"
+entryp :: JournalParser m Transaction
+entryp = do
+  lift $ traceparse "  entryp"
   pos <- genericSourcePos <$> getSourcePos
   lift $ optional $ choice [orgheadingprefixp, skipSome spacenonewline]
   a <- modifiedaccountnamep
   lift (skipMany spacenonewline)
   hours <-
     try (lift followingcommentp >> return 0)
-    <|> (timedotdurationp <*
+    <|> (durationp <*
          (try (lift followingcommentp) <|> (newline >> return "")))
   let t = nulltransaction{
         tsourcepos = pos,
@@ -150,8 +189,8 @@ timedotentryp = do
         }
   return t
 
-timedotdurationp :: JournalParser m Quantity
-timedotdurationp = try timedotnumericp <|> timedotdotsp
+durationp :: JournalParser m Quantity
+durationp = try numericquantityp <|> dotquantityp
 
 -- | Parse a duration of seconds, minutes, hours, days, weeks, months or years,
 -- written as a decimal number followed by s, m, h, d, w, mo or y, assuming h
@@ -162,8 +201,8 @@ timedotdurationp = try timedotnumericp <|> timedotdotsp
 -- 1.5h
 -- 90m
 -- @
-timedotnumericp :: JournalParser m Quantity
-timedotnumericp = do
+numericquantityp :: JournalParser m Quantity
+numericquantityp = do
   (q, _, _, _) <- lift $ numberp Nothing
   msymbol <- optional $ choice $ map (string . fst) timeUnits
   lift (skipMany spacenonewline)
@@ -191,7 +230,7 @@ timeUnits =
 -- @
 -- .... ..
 -- @
-timedotdotsp :: JournalParser m Quantity
-timedotdotsp = do
+dotquantityp :: JournalParser m Quantity
+dotquantityp = do
   dots <- filter (not.isSpace) <$> many (oneOf (". " :: [Char]))
   return $ (/4) $ fromIntegral $ length dots