Text.Pandoc.Shared

Utility functions and definitions used by the various Pandoc modules.

List processing

splitBy :: (a -> Bool) -> [a] -> [[a]]

Split list by groups of one or more sep.

splitByIndices :: [Int] -> [a] -> [[a]]

splitStringByIndices :: [Int] -> [Char] -> [[Char]]

Split string into chunks divided at specified indices.

substitute :: Eq a => [a] -> [a] -> [a] -> [a]

Replace each occurrence of one sublist in a list with another.

ordNub :: Ord a => [a] -> [a]

Text processing

backslashEscapes

Arguments

:: [Char]

list of special characters to escape

-> [(Char, String)]

Returns an association list of backslash escapes for the designated characters.

escapeStringUsing :: [(Char, String)] -> String -> String

Escape a string of characters, using an association list of characters and strings.

stripTrailingNewlines :: String -> String

Strip trailing newlines from string.

trim :: String -> String

Remove leading and trailing space (including newlines) from string.

triml :: String -> String

Remove leading space (including newlines) from string.

trimr :: String -> String

Remove trailing space (including newlines) from string.

stripFirstAndLast :: String -> String

Strip leading and trailing characters from string

camelCaseToHyphenated :: String -> String

Change CamelCase word to hyphenated lowercase (e.g., camel-case).

toRomanNumeral :: Int -> String

Convert number < 4000 to uppercase roman numeral.

escapeURI :: String -> String

Escape whitespace and some punctuation characters in URI.

tabFilter

Arguments

:: Int

Tab stop

-> String

Input

-> String

Convert tabs to spaces and filter out DOS line endings. Tabs will be preserved if tab stop is set to 0.

Date/time

normalizeDate :: String -> Maybe String

Parse a date and convert (if possible) to YYYY-MM-DD format. We limit years to the range 1601-9999 (ISO 8601 accepts greater than or equal to 1583, but MS Word only accepts dates starting 1601).

Pandoc block and inline list processing

orderedListMarkers :: (Int, ListNumberStyle, ListNumberDelim) -> [String]

Generate infinite lazy list of markers for an ordered list, depending on list attributes.

normalizeSpaces :: [Inline] -> [Inline]

Normalize a list of inline elements: remove leading and trailing Space elements, collapse double Spaces into singles, and remove empty Str elements.

extractSpaces :: (Inlines -> Inlines) -> Inlines -> Inlines

Extract the leading and trailing spaces from inside an inline element and place them outside the element. SoftBreaks count as Spaces for these purposes.

normalize :: Pandoc -> Pandoc

Normalize Pandoc document, consolidating doubled Spaces, combining adjacent Strs and Emphs, remove Nulls and empty elements, etc.

normalizeInlines :: [Inline] -> [Inline]

normalizeBlocks :: [Block] -> [Block]

removeFormatting :: Walkable Inline a => a -> [Inline]

Extract inlines, removing formatting.

stringify :: Walkable Inline a => a -> String

Convert pandoc structure to a string with formatting removed. Footnotes are skipped (since we don't want their contents in link labels).

capitalize :: Walkable Inline a => a -> a

Bring all regular text in a pandoc structure to uppercase.

This function correctly handles cases where a lowercase character doesn't match to a single uppercase character – e.g. “Straße” would be converted to “STRASSE”, not “STRAßE”.

compactify

Arguments

:: [[Block]]

List of list items (each a list of blocks)

-> [[Block]]

Change final list item from Para to Plain if the list contains no other Para blocks.

compactify'

Arguments

:: [Blocks]

List of list items (each a list of blocks)

-> [Blocks]

Change final list item from Para to Plain if the list contains no other Para blocks. Like compactify, but operates on Blocks rather than [Block].

compactify'DL :: [(Inlines, [Blocks])] -> [(Inlines, [Blocks])]

Like compactify', but acts on items of definition lists.

linesToPara :: [[Inline]] -> Block

Convert a list of lines into a paragraph with hard line breaks. This is useful e.g. for rudimentary support of LineBlock elements in writers.

data Element

Data structure for defining hierarchical Pandoc documents

Constructors

Blk Block

Sec Int [Int] Attr [Inline] [Element]

Instances

Eq Element

Methods

(==) :: Element -> Element -> Bool

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

Data Element

Methods

gfoldl :: (forall d b. Data d => c (d -> b) -> d -> c b) -> (forall g. g -> c g) -> Element -> c Element

gunfold :: (forall b r. Data b => c (b -> r) -> c r) -> (forall r. r -> c r) -> Constr -> c Element

toConstr :: Element -> Constr

dataTypeOf :: Element -> DataType

dataCast1 :: Typeable (* -> *) t => (forall d. Data d => c (t d)) -> Maybe (c Element)

dataCast2 :: Typeable (* -> * -> *) t => (forall d e. (Data d, Data e) => c (t d e)) -> Maybe (c Element)

gmapT :: (forall b. Data b => b -> b) -> Element -> Element

gmapQl :: (r -> r' -> r) -> r -> (forall d. Data d => d -> r') -> Element -> r

gmapQr :: (r' -> r -> r) -> r -> (forall d. Data d => d -> r') -> Element -> r

gmapQ :: (forall d. Data d => d -> u) -> Element -> [u]

gmapQi :: Int -> (forall d. Data d => d -> u) -> Element -> u

gmapM :: Monad m => (forall d. Data d => d -> m d) -> Element -> m Element

gmapMp :: MonadPlus m => (forall d. Data d => d -> m d) -> Element -> m Element

gmapMo :: MonadPlus m => (forall d. Data d => d -> m d) -> Element -> m Element

Read Element

Methods

readsPrec :: Int -> ReadS Element

readList :: ReadS [Element]

readPrec :: ReadPrec Element

readListPrec :: ReadPrec [Element]

Show Element

Methods

showsPrec :: Int -> Element -> ShowS

show :: Element -> String

showList :: [Element] -> ShowS

Walkable Block Element

Methods

walk :: (Block -> Block) -> Element -> Element

walkM :: (Monad m, Functor m) => (Block -> m Block) -> Element -> m Element

query :: Monoid c => (Block -> c) -> Element -> c

Walkable Inline Element

Methods

walk :: (Inline -> Inline) -> Element -> Element

walkM :: (Monad m, Functor m) => (Inline -> m Inline) -> Element -> m Element

query :: Monoid c => (Inline -> c) -> Element -> c

hierarchicalize :: [Block] -> [Element]

Convert list of Pandoc blocks into (hierarchical) list of Elements

uniqueIdent :: [Inline] -> Set String -> String

Generate a unique identifier from a list of inlines. Second argument is a list of already used identifiers.

inlineListToIdentifier :: [Inline] -> String

Convert Pandoc inline list to plain text identifier. HTML identifiers must start with a letter, and may contain only letters, digits, and the characters _-.

isHeaderBlock :: Block -> Bool

True if block is a Header block.

headerShift :: Int -> Pandoc -> Pandoc

Shift header levels up or down.

isTightList :: [[Block]] -> Bool

Detect if a list is tight.

addMetaField :: ToMetaValue a => String -> a -> Meta -> Meta

Set a field of a Meta object. If the field already has a value, convert it into a list with the new value appended to the old value(s).

makeMeta :: [Inline] -> [[Inline]] -> [Inline] -> Meta

Create Meta from old-style title, authors, date. This is provided to ease the transition from the old API.

TagSoup HTML handling

renderTags' :: [Tag String] -> String

Render HTML tags.

File handling

inDirectory :: FilePath -> IO a -> IO a

Perform an IO action in a directory, returning to starting directory.

getDefaultReferenceDocx :: Maybe FilePath -> IO Archive

getDefaultReferenceODT :: Maybe FilePath -> IO Archive

readDataFile :: Maybe FilePath -> FilePath -> IO ByteString

Read file from specified user data directory or, if not found there, from Cabal data directory.

readDataFileUTF8 :: Maybe FilePath -> FilePath -> IO String

Same as readDataFile but returns a String instead of a ByteString.

fetchItem :: Maybe String -> String -> IO (Either SomeException (ByteString, Maybe MimeType))

Fetch an image or other item from the local filesystem or the net. Returns raw content and maybe mime type.

fetchItem' :: MediaBag -> Maybe String -> String -> IO (Either SomeException (ByteString, Maybe MimeType))

Like fetchItem, but also looks for items in a MediaBag.

openURL :: String -> IO (Either SomeException (ByteString, Maybe MimeType))

Read from a URL and return raw data and maybe mime type.

collapseFilePath :: FilePath -> FilePath

Remove intermediate "." and ".." directories from a path.

collapseFilePath "./foo" == "foo"
collapseFilePath "/bar/../baz" == "/baz"
collapseFilePath "/../baz" == "/../baz"
collapseFilePath "parent/foo/baz/../bar" ==  "parent/foo/bar"
collapseFilePath "parent/foo/baz/../../bar" ==  "parent/bar"
collapseFilePath "parent/foo/.." ==  "parent"
collapseFilePath "/parent/foo/../../bar" ==  "/bar"

filteredFilesFromArchive :: Archive -> (FilePath -> Bool) -> [(FilePath, ByteString)]

Error handling

err :: Int -> String -> IO a

warn :: MonadIO m => String -> m ()

mapLeft :: (a -> b) -> Either a c -> Either b c

hush :: Either a b -> Maybe b

for squashing blocks

blocksToInlines :: [Block] -> [Inline]

Safe read

safeRead :: (MonadPlus m, Read a) => String -> m a

Temp directory

withTempDir :: String -> (FilePath -> IO a) -> IO a

Version

pandocVersion :: String

Version number of pandoc library.