Codec.Xlsx.Parser.Stream

Parse .xlsx sheets in constant memory.

All actions on an xlsx file run inside the XlsxM monad, and must be run with runXlsxM. XlsxM is not a monad transformer, a design inherited from the "zip" package's ZipArchive monad.

Inside the XlsxM monad, you can stream SheetItems (a row) from a particular sheet, using readSheetByIndex, which is callback-based and tied to IO.

Documentation

data XlsxM a

Instances

Monad XlsxM

Defined in Codec.Xlsx.Parser.Stream

Methods

(>>=) :: XlsxM a -> (a -> XlsxM b) -> XlsxM b

(>>) :: XlsxM a -> XlsxM b -> XlsxM b

return :: a -> XlsxM a

Functor XlsxM

Defined in Codec.Xlsx.Parser.Stream

Methods

fmap :: (a -> b) -> XlsxM a -> XlsxM b

(<$) :: a -> XlsxM b -> XlsxM a

Applicative XlsxM

Defined in Codec.Xlsx.Parser.Stream

Methods

pure :: a -> XlsxM a

(<*>) :: XlsxM (a -> b) -> XlsxM a -> XlsxM b

liftA2 :: (a -> b -> c) -> XlsxM a -> XlsxM b -> XlsxM c

(*>) :: XlsxM a -> XlsxM b -> XlsxM b

(<*) :: XlsxM a -> XlsxM b -> XlsxM a

MonadIO XlsxM

Defined in Codec.Xlsx.Parser.Stream

Methods

liftIO :: IO a -> XlsxM a

MonadThrow XlsxM

Defined in Codec.Xlsx.Parser.Stream

Methods

throwM :: Exception e => e -> XlsxM a

MonadCatch XlsxM

Defined in Codec.Xlsx.Parser.Stream

Methods

catch :: Exception e => XlsxM a -> (e -> XlsxM a) -> XlsxM a

MonadMask XlsxM

Defined in Codec.Xlsx.Parser.Stream

Methods

mask :: ((forall a. XlsxM a -> XlsxM a) -> XlsxM b) -> XlsxM b

uninterruptibleMask :: ((forall a. XlsxM a -> XlsxM a) -> XlsxM b) -> XlsxM b

generalBracket :: XlsxM a -> (a -> ExitCase b -> XlsxM c) -> (a -> XlsxM b) -> XlsxM (b, c)

MonadBase IO XlsxM

Defined in Codec.Xlsx.Parser.Stream

Methods

liftBase :: IO α -> XlsxM α

MonadBaseControl IO XlsxM

Defined in Codec.Xlsx.Parser.Stream

Associated Types

type StM XlsxM a

Methods

liftBaseWith :: (RunInBase XlsxM IO -> IO a) -> XlsxM a

restoreM :: StM XlsxM a -> XlsxM a

type StM XlsxM a

Defined in Codec.Xlsx.Parser.Stream

type StM XlsxM a

runXlsxM :: MonadIO m => FilePath -> XlsxM a -> m a

Run a series of actions on an Xlsx file

data WorkbookInfo

Information about the workbook contained in xl/workbook.xml (currently a subset)

Constructors

WorkbookInfo

Fields

• _wiSheets :: [SheetInfo]

Instances

Show WorkbookInfo

Defined in Codec.Xlsx.Parser.Stream

Methods

showsPrec :: Int -> WorkbookInfo -> ShowS

show :: WorkbookInfo -> String

showList :: [WorkbookInfo] -> ShowS

data SheetInfo

Represents sheets from the workbook.xml file. E.g. <sheet name=Data sheetId="1" state="hidden" r:id="rId2" /

Constructors

SheetInfo

Fields

• sheetInfoName :: Text
• sheetInfoRelId :: RefId

  The r:id attribute value.

• sheetInfoSheetId :: Int

  The sheetId attribute value

Instances

Eq SheetInfo

Defined in Codec.Xlsx.Parser.Stream

Methods

(==) :: SheetInfo -> SheetInfo -> Bool

(/=) :: SheetInfo -> SheetInfo -> Bool

Show SheetInfo

Defined in Codec.Xlsx.Parser.Stream

Methods

showsPrec :: Int -> SheetInfo -> ShowS

show :: SheetInfo -> String

showList :: [SheetInfo] -> ShowS

wiSheets :: Iso' WorkbookInfo [SheetInfo]

getWorkbookInfo :: XlsxM WorkbookInfo

Returns information about the workbook, found in xl/workbook.xml. The result is cached so the XML will only be decompressed and parsed once inside a larger XlsxM action.

type CellRow = IntMap Cell

readSheet

Arguments

:: SheetIndex

-> (SheetItem -> IO ())

Function to consume the sheet's rows

-> XlsxM Bool

Returns False if sheet doesn't exist, or True otherwise

countRowsInSheet :: SheetIndex -> XlsxM (Maybe Int)

Returns number of rows in the given sheet (identified by the sheet's ID, AKA the sheetId attribute, AKA sheetInfoSheetId), or Nothing if the sheet does not exist. Does not perform a full parse of the XML into SheetItems, so it should be more efficient than counting via readSheetByIndex.

collectItems :: SheetIndex -> XlsxM [SheetItem]

this will collect the sheetitems in a list. useful for cases were memory is of no concern but a sheetitem type in a list is needed.

Index

data SheetIndex

datatype representing a sheet index, looking it up by name can be done with makeIndexFromName, which is the preferred approach. although makeIndex is available in case it's already known.

Instances

NFData SheetIndex

Defined in Codec.Xlsx.Parser.Stream

Methods

rnf :: SheetIndex -> ()

makeIndex :: Int -> SheetIndex

This does *no* checking if the index exists or not. you could have index out of bounds issues because of this.

makeIndexFromName :: Text -> XlsxM (Maybe SheetIndex)

Look up the index of a case insensitive sheet name

SheetItem

data SheetItem

Sheet item

The current sheet at a time, every sheet is constructed of these items.

Constructors

MkSheetItem

Fields

• _si_sheet_index :: Int

  The sheet number

• _si_row :: ~Row

Instances

Show SheetItem

Defined in Codec.Xlsx.Parser.Stream

Methods

showsPrec :: Int -> SheetItem -> ShowS

show :: SheetItem -> String

showList :: [SheetItem] -> ShowS

Generic SheetItem

Defined in Codec.Xlsx.Parser.Stream

Associated Types

type Rep SheetItem :: Type -> Type

Methods

from :: SheetItem -> Rep SheetItem x

to :: Rep SheetItem x -> SheetItem

NFData SheetItem

Defined in Codec.Xlsx.Parser.Stream

Methods

rnf :: SheetItem -> ()

type Rep SheetItem

Defined in Codec.Xlsx.Parser.Stream

type Rep SheetItem = D1 ('MetaData "SheetItem" "Codec.Xlsx.Parser.Stream" "xlsx-1.0.0.1-inplace" 'False) (C1 ('MetaCons "MkSheetItem" 'PrefixI 'True) (S1 ('MetaSel ('Just "_si_sheet_index") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 Int) :*: S1 ('MetaSel ('Just "_si_row") 'NoSourceUnpackedness 'SourceLazy 'DecidedLazy) (Rec0 Row)))

si_sheet_index :: Lens' SheetItem Int

si_row :: Lens' SheetItem Row

Row

data Row

Constructors

MkRow

Fields

• _ri_row_index :: Int

  Row number

• _ri_cell_row :: ~CellRow

  Row itself

Instances

Show Row

Defined in Codec.Xlsx.Parser.Stream

Methods

showsPrec :: Int -> Row -> ShowS

show :: Row -> String

showList :: [Row] -> ShowS

Generic Row

Defined in Codec.Xlsx.Parser.Stream

Associated Types

type Rep Row :: Type -> Type

Methods

from :: Row -> Rep Row x

to :: Rep Row x -> Row

NFData Row

Defined in Codec.Xlsx.Parser.Stream

Methods

rnf :: Row -> ()

type Rep Row

Defined in Codec.Xlsx.Parser.Stream

type Rep Row = D1 ('MetaData "Row" "Codec.Xlsx.Parser.Stream" "xlsx-1.0.0.1-inplace" 'False) (C1 ('MetaCons "MkRow" 'PrefixI 'True) (S1 ('MetaSel ('Just "_ri_row_index") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 Int) :*: S1 ('MetaSel ('Just "_ri_cell_row") 'NoSourceUnpackedness 'SourceLazy 'DecidedLazy) (Rec0 CellRow)))

ri_row_index :: Lens' Row Int

ri_cell_row :: Lens' Row CellRow

Errors

data SheetErrors

Constructors

ParseCoordinateError CoordinateErrors

Error while parsing coordinates

ParseTypeError TypeError

Error while parsing types

ParseCellError AddCellErrors

Error while parsing cells

ParseStyleErrors StyleError

HexpatParseError XMLParseError

Instances

Show SheetErrors

Defined in Codec.Xlsx.Parser.Stream

Methods

showsPrec :: Int -> SheetErrors -> ShowS

show :: SheetErrors -> String

showList :: [SheetErrors] -> ShowS

Exception SheetErrors

Defined in Codec.Xlsx.Parser.Stream

Methods

toException :: SheetErrors -> SomeException

fromException :: SomeException -> Maybe SheetErrors

displayException :: SheetErrors -> String

data AddCellErrors

Constructors

ReadError

Could not read current cell value

Fields

• Text

  Original value

• String

  Error message

SharedStringsNotFound

Could not find string by index in shared string table

Fields

• Int

  Given index

• (Vector Text)

  Given shared strings to lookup in

Instances

Show AddCellErrors

Defined in Codec.Xlsx.Parser.Stream

Methods

showsPrec :: Int -> AddCellErrors -> ShowS

show :: AddCellErrors -> String

showList :: [AddCellErrors] -> ShowS

data CoordinateErrors

Constructors

CoordinateNotFound SheetValues

If the coordinate was not specified in "r" attribute

NoListElement SheetValue SheetValues

If the value is empty for some reason

NoTextContent Content SheetValues

If the value has something besides ContentText inside

DecodeFailure Text SheetValues

If malformed coordinate text was passed

Instances

Show CoordinateErrors

Defined in Codec.Xlsx.Parser.Stream

Methods

showsPrec :: Int -> CoordinateErrors -> ShowS

show :: CoordinateErrors -> String

showList :: [CoordinateErrors] -> ShowS

Exception CoordinateErrors

Defined in Codec.Xlsx.Parser.Stream

Methods

toException :: CoordinateErrors -> SomeException

fromException :: SomeException -> Maybe CoordinateErrors

displayException :: CoordinateErrors -> String

data TypeError

Constructors

TypeNotFound SheetValues

TypeNoListElement SheetValue SheetValues

UnkownType Text SheetValues

TypeNoTextContent Content SheetValues

Instances

Show TypeError

Defined in Codec.Xlsx.Parser.Stream

Methods

showsPrec :: Int -> TypeError -> ShowS

show :: TypeError -> String

showList :: [TypeError] -> ShowS

Exception TypeError

Defined in Codec.Xlsx.Parser.Stream

Methods

toException :: TypeError -> SomeException

fromException :: SomeException -> Maybe TypeError

displayException :: TypeError -> String

data WorkbookError

Constructors

LookupError

Fields

• lookup_attrs :: [(ByteString, Text)]
• lookup_field :: ByteString

ParseDecimalError Text String

Instances

Show WorkbookError

Defined in Codec.Xlsx.Parser.Stream

Methods

showsPrec :: Int -> WorkbookError -> ShowS

show :: WorkbookError -> String

showList :: [WorkbookError] -> ShowS

Exception WorkbookError

Defined in Codec.Xlsx.Parser.Stream

Methods

toException :: WorkbookError -> SomeException

fromException :: SomeException -> Maybe WorkbookError

displayException :: WorkbookError -> String