Skip to content

[fork validation] RFC 4180 quoting in toSeparated #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
skymanbp wants to merge 1 commit into
base: main
Choose a base branch
from
Open

[fork validation] RFC 4180 quoting in toSeparated #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 12 additions & 2 deletions dataframe-core/src-internal/DataFrame/Internal/DataFrame.hs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -335,10 +335,20 @@ toSeparated sep df
let (rows, _) = dataframeDimensions df
headers = map fst (sortBy (compare `on` snd) (M.toList (columnIndices df)))
sepText = T.singleton sep
headerLine = T.intercalate sepText headers
dataLines = map (T.intercalate sepText . getRowAsText df) [0 .. rows - 1]
escape = escapeField sep
headerLine = T.intercalate sepText (map escape headers)
dataLines =
map (T.intercalate sepText . map escape . getRowAsText df) [0 .. rows - 1]
in T.unlines (headerLine : dataLines)

-- | RFC 4180: quote fields with sep, quote or newline; double inner quotes.
escapeField :: Char -> T.Text -> T.Text
escapeField sep t
| T.any needsQuoting t = "\"" <> T.replace "\"" "\"\"" t <> "\""
| otherwise = t
where
needsQuoting c = c == sep || c == '"' || c == '\n' || c == '\r'

getRowAsText :: DataFrame -> Int -> [T.Text]
getRowAsText df i = map (`showElement` i) (V.toList (columns df))

Expand Down
14 changes: 14 additions & 0 deletions tests/IO/CSV.hs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,6 +86,19 @@ fromCsvSingleColumn = TestLabel "fromCsv_single_column" $ TestCase $ do
assertEqual "rows" 3 (D.nRows df)
assertEqual "columns" 1 (D.nColumns df)

-- | Round trip: fields holding separators, quotes and newlines survive.
fromCsvRoundTripQuoted :: Test
fromCsvRoundTripQuoted = TestLabel "fromCsv_roundTrip_quoted" $ TestCase $ do
let df =
D.fromNamedColumns
[ ("a,b", DI.fromList @T.Text ["x,y", "he said \"hi\"", "line1\nline2"])
, ("c", DI.fromList @Int [1, 2, 3])
]
result <- fromCsv (T.unpack (toCsv df))
case result of
Left err -> assertFailure $ "Unexpected Left: " ++ err
Right df' -> assertEqual "round trip data" df df'

tests :: [Test]
tests =
[ fromCsvHappyPath
Expand All @@ -94,4 +107,5 @@ tests =
, fromCsvRoundTrip
, fromCsvBytesRoundTrip
, fromCsvSingleColumn
, fromCsvRoundTripQuoted
]
Loading