import Parsing
{- A CSV file contains 0 or more lines, each of which is terminated
   by the newline character. -}
csv = zeroOrMore line

-- each line contains one or more cells, separated by a comma 
line = do 
   cells <- chain cell (char comma)
   char newline
   return cells

-- 

-- A cell is either an ordinary cell or a quoted cell.
cell = quotedcell +++ ordinarycell

-- An ordinary cell is a sequence of characters not including 
-- comma or newline.  
ordinarycell = zeroOrMore $ sat (`notElem` [comma,newline])

-- A quoted cell "thus" is a sequence of zero or more characters
-- other than double quote.
quotedcell = do 
  char quote
  cs <- zeroOrMore $ sat (/= quote)
  char quote
  return cs

comma   = ','
quote   = '\"'
newline = '\n'

wikiExample = unlines [l1,l2,l3,l4,l5]
l1 = "Year,Make,Model,Description,Price"
l2 = "1997,Ford,E350,\"ac, abs, moon\",3000.00"
l3 = "1999,Chevy,Venture \"Extended Edition\",\"\",4900.00"
l4 = "1999,Chevy,Venture \"Extended Edition, Very Large\",,5000.00"
l5 = "1996,Jeep,Grand Cherokee,\"MUST SELL!\nair, moon roof, loaded\",4799.00" 
               

{-
-- The whole thing in 4 lines:
csv  = zeroOrMore line 
line = chain cell (char comma) <-< char newline
cell = char quote >-> zeroOrMore (sat (/= quote)) <-< char quote
   +++ zeroOrMore (sat (`notElem` [comma,newline]))
[comma,quote,newline] = ",\"\n"
 -}