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.

splitTextBy :: (Char -> Bool) -> Text -> [Text]

Split text by groups of one or more separator.

splitTextByIndices :: [Int] -> Text -> [Text]

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

findM :: forall m t a. (Monad m, Foldable t) => (a -> m Bool) -> t a -> m (Maybe a)

Text processing

tshow :: Show a => a -> Text

elemText :: Char -> Text -> Bool

True exactly when the Char appears in the Text.

notElemText :: Char -> Text -> Bool

True exactly when the Char does not appear in the Text.

stripTrailingNewlines :: Text -> Text

Strip trailing newlines from string.

trim :: Text -> Text

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

triml :: Text -> Text

Remove leading space (including newlines) from string.

trimr :: Text -> Text

Remove trailing space (including newlines) from string.

trimMath :: Text -> Text

Trim leading space and trailing space unless after .

stripFirstAndLast :: Text -> Text

Strip leading and trailing characters from string

camelCaseToHyphenated :: Text -> Text

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

camelCaseStrToHyphenated :: String -> String

toRomanNumeral :: Int -> Text

Convert number < 4000 to uppercase roman numeral.

escapeURI :: Text -> Text

Escape whitespace and some punctuation characters in URI.

tabFilter

Arguments

:: Int

Tab stop

-> Text

Input

-> Text

Convert tabs to spaces. Tabs will be preserved if tab stop is set to 0.

crFilter :: Text -> Text

Deprecated: readers filter crs automatically

Strip out DOS line endings.

Date/time

normalizeDate :: Text -> Maybe Text

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) -> [Text]

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

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.

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

Extract inlines, removing formatting.

deNote :: Inline -> Inline

deLink :: Inline -> Inline

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

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

:: [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. Otherwise (if the list items contain Para blocks besides possibly at the end), turn any Plains into Paras (#5285).

compactifyDL :: [(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.

makeSections :: Bool -> Maybe Int -> [Block] -> [Block]

Put a list of Pandoc blocks into a hierarchical structure: a list of sections (each a Div with class "section" and first element a Header). If the numbering parameter is True, Header numbers are added via the number attribute on the header. If the baseLevel parameter is Just n, Header levels are adjusted to be gapless starting at level n.

uniqueIdent :: Extensions -> [Inline] -> Set Text -> Text

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

inlineListToIdentifier :: Extensions -> [Inline] -> Text

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.

stripEmptyParagraphs :: Pandoc -> Pandoc

Remove empty paragraphs.

onlySimpleTableCells :: [[[Block]]] -> Bool

Detect if table rows contain only cells consisting of a single paragraph that has no LineBreak.

isTightList :: [[Block]] -> Bool

Detect if a list is tight.

taskListItemFromAscii :: Extensions -> [Block] -> [Block]

Convert a list item containing tasklist syntax (e.g. [x]) to using U+2610 BALLOT BOX or U+2612 BALLOT BOX WITH X.

taskListItemToAscii :: Extensions -> [Block] -> [Block]

Convert a list item containing text starting with U+2610 BALLOT BOX or U+2612 BALLOT BOX WITH X to tasklist syntax (e.g. [x]).

handleTaskListItem :: ([Inline] -> [Inline]) -> Extensions -> [Block] -> [Block]

addMetaField :: ToMetaValue a => Text -> 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.

eastAsianLineBreakFilter :: Pandoc -> Pandoc

Remove soft breaks between East Asian characters.

htmlSpanLikeElements :: Set Text

Set of HTML elements that are represented as Span with a class equal as the element tag itself.

splitSentences :: [Inline] -> [[Inline]]

Split a list of inlines into sentences.

filterIpynbOutput :: Maybe Format -> Pandoc -> Pandoc

Process ipynb output cells. If mode is Nothing, remove all output. If mode is Just format, select best output for the format. If format is not ipynb, strip out ANSI escape sequences from CodeBlocks (see #5633).

TagSoup HTML handling

renderTags' :: [Tag Text] -> Text

Render HTML tags.

File handling

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

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

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"

uriPathToPath :: Text -> FilePath

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

URI handling

schemes :: Set Text

Schemes from http://www.iana.org/assignments/uri-schemes.html plus the unofficial schemes doi, javascript, isbn, pmid.

isURI :: Text -> Bool

Check if the string is a valid URL with a IANA or frequently used but unofficial scheme (see schemes).

Error handling

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

for squashing blocks

blocksToInlines :: [Block] -> [Inline]

blocksToInlines' :: [Block] -> Inlines

blocksToInlinesWithSep :: Inlines -> [Block] -> Inlines

defaultBlocksSeparator :: Inlines

Inline elements used to separate blocks when squashing blocks into inlines.

Safe read

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

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

User data directory

defaultUserDataDir :: IO FilePath

Return appropriate user data directory for platform. We use XDG_DATA_HOME (or its default value), but for backwards compatibility, we fall back to the legacy user data directory ($HOME/.pandoc on *nix) if the XDG_DATA_HOME is missing and this exists. If neither directory is present, we return the XDG data directory.

Version

pandocVersion :: Text

Version number of pandoc library.