-- Hoogle documentation, generated by Haddock -- See Hoogle, http://www.haskell.org/hoogle/ -- | Reading, writing and manipulating ".tar" archive files. -- @package tar @version 0.4.2.1 -- | Random access to the content of a .tar archive. -- -- This module uses common names and so is designed to be imported -- qualified: -- -- 
--   import qualified Codec.Archive.Tar.Index as Tar
--
module Codec.Archive.Tar.Index -- | An index of the entries in a tar file. -- -- This index type is designed to be quite compact and suitable to store -- either on disk or in memory. data TarIndex -- | Look up a given filepath in the TarIndex. It may return a -- TarFileEntry containing the TarEntryOffset of the file -- within the tar file, or if the filepath identifies a directory then it -- returns a TarDir containing the list of files within that -- directory. -- -- Given the TarEntryOffset you can then use one of the I/O -- operations: -- -- lookup :: TarIndex -> FilePath -> Maybe TarIndexEntry -- | The result of lookup in a TarIndex. It can either be a -- file directly, or a directory entry containing further entries (and -- all subdirectories recursively). Note that the subtrees are -- constructed lazily, so it's cheaper if you don't look at them. data TarIndexEntry TarFileEntry :: {-# UNPACK #-} !TarEntryOffset -> TarIndexEntry TarDir :: [(FilePath, TarIndexEntry)] -> TarIndexEntry -- | An offset within a tar file. Use hReadEntry, -- hReadEntryHeader or hSeekEntryOffset. -- -- This is actually a tar "record" number, not a byte offset. type TarEntryOffset = Word32 -- | Reads an entire Entry at the given TarEntryOffset in the -- tar file. The Handle must be open for reading and be seekable. -- -- This reads the whole entry into memory strictly, not incrementally. -- For more control, use hReadEntryHeader and then read the entry -- content manually. hReadEntry :: Handle -> TarEntryOffset -> IO Entry -- | Read the header for a Entry at the given TarEntryOffset -- in the tar file. The entryContent will contain the correct -- metadata but an empty file content. The Handle must be open for -- reading and be seekable. -- -- The Handle position is advanced to the beginning of the entry -- content (if any). You must check the entryContent to see if the -- entry is of type NormalFile. If it is, the NormalFile -- gives the content length and you are free to read this much data from -- the Handle. -- -- 
--   entry <- Tar.hReadEntryHeader hnd
--   case Tar.entryContent entry of
--     Tar.NormalFile _ size -> do content <- BS.hGet hnd size
--                                 ...
--
-- -- Of course you don't have to read it all in one go (as -- hReadEntry does), you can use any appropriate method to read it -- incrementally. -- -- In addition to I/O errors, this can throw a FormatError if the -- offset is wrong, or if the file is not valid tar format. -- -- There is also the lower level operation hSeekEntryOffset. hReadEntryHeader :: Handle -> TarEntryOffset -> IO Entry -- | Build a TarIndex from a sequence of tar Entries. The -- Entries are assumed to start at offset 0 within a -- file. build :: Entries e -> Either e TarIndex -- | The intermediate type used for incremental construction of a -- TarIndex. data IndexBuilder -- | The initial empty IndexBuilder. emptyIndex :: IndexBuilder -- | Add the next Entry into the IndexBuilder. addNextEntry :: Entry -> IndexBuilder -> IndexBuilder -- | Use this function if you want to skip some entries and not add them to -- the final TarIndex. skipNextEntry :: Entry -> IndexBuilder -> IndexBuilder -- | Finish accumulating Entry information and build the compact -- TarIndex lookup structure. finaliseIndex :: IndexBuilder -> TarIndex -- | The TarIndex is compact in memory, and it has a similarly -- compact external representation. serialise :: TarIndex -> Builder -- | Read the external representation back into a TarIndex. deserialise :: ByteString -> Maybe (TarIndex, ByteString) -- | This is a low level variant on hReadEntryHeader, that can be -- used to iterate through a tar file, entry by entry. -- -- It has a few differences compared to hReadEntryHeader: -- -- -- -- After this action, the Handle position is not in any useful -- place. If you want to skip to the next entry, take the -- TarEntryOffset returned and use hReadEntryHeaderOrEof -- again. Or if having inspected the Entry header you want to read -- the entry content (if it has one) then use -- hSeekEntryContentOffset on the original input -- TarEntryOffset. hReadEntryHeaderOrEof :: Handle -> TarEntryOffset -> IO (Maybe (Entry, TarEntryOffset)) -- | Set the Handle position to the position corresponding to the -- given TarEntryOffset. -- -- This position is where the entry metadata can be read. If you already -- know the entry has a body (and perhaps know it's length), you may wish -- to seek to the body content directly using -- hSeekEntryContentOffset. hSeekEntryOffset :: Handle -> TarEntryOffset -> IO () -- | Set the Handle position to the entry content position -- corresponding to the given TarEntryOffset. -- -- This position is where the entry content can be read using ordinary -- I/O operations (though you have to know in advance how big the entry -- content is). This is only valid if you already know the -- entry has a body (i.e. is a normal file). hSeekEntryContentOffset :: Handle -> TarEntryOffset -> IO () -- | Seek to the end of a tar file, to the position where new entries can -- be appended, and return that TarEntryOffset. -- -- If you have a valid TarIndex for this tar file then you should -- supply it because it allows seeking directly to the correct location. -- -- If you do not have an index, then this becomes an expensive linear -- operation because we have to read each tar entry header from the -- beginning to find the location immediately after the last entry (this -- is because tar files have a variable length trailer and we cannot -- reliably find that by starting at the end). In this mode, it will fail -- with an exception if the file is not in fact in the tar format. hSeekEndEntryOffset :: Handle -> Maybe TarIndex -> IO TarEntryOffset -- | Calculate the TarEntryOffset of the next entry, given the size -- and offset of the current entry. -- -- This is much like using skipNextEntry and -- indexNextEntryOffset, but without using an IndexBuilder. nextEntryOffset :: Entry -> TarEntryOffset -> TarEntryOffset -- | This is the offset immediately following the last entry in the tar -- file. This can be useful to append further entries into the tar file. -- Use with hSeekEntryOffset, or just use -- hSeekEndEntryOffset directly. indexEndEntryOffset :: TarIndex -> TarEntryOffset -- | This is the offset immediately following the entry most recently added -- to the IndexBuilder. You might use this if you need to know the -- offsets but don't want to use the TarIndex lookup structure. -- Use with hSeekEntryOffset. See also nextEntryOffset. indexNextEntryOffset :: IndexBuilder -> TarEntryOffset instance Typeable PathComponentId instance Typeable TarIndexEntry instance Typeable TarIndex instance Eq PathComponentId instance Ord PathComponentId instance Enum PathComponentId instance Show PathComponentId instance Show TarIndexEntry instance Eq TarIndex instance Show TarIndex -- | Perform various checks on tar file entries. module Codec.Archive.Tar.Check -- | This function checks a sequence of tar entries for file name security -- problems. It checks that: -- -- -- -- These checks are from the perspective of the current OS. That means we -- check for "C:blah" files on Windows and "/blah" files on -- Unix. For archive entry types HardLink and SymbolicLink -- the same checks are done for the link target. A failure in any entry -- terminates the sequence of entries with an error. checkSecurity :: Entries e -> Entries (Either e FileNameError) -- | Errors arising from tar file names being in some way invalid or -- dangerous data FileNameError InvalidFileName :: FilePath -> FileNameError AbsoluteFileName :: FilePath -> FileNameError -- | This function checks a sequence of tar entries for being a "tar bomb". -- This means that the tar file does not follow the standard convention -- that all entries are within a single subdirectory, e.g. a file -- "foo.tar" would usually have all entries within the "foo/" -- subdirectory. -- -- Given the expected subdirectory, this function checks all entries are -- within that subdirectroy. -- -- Note: This check must be used in conjunction with checkSecurity -- (or checkPortability). checkTarbomb :: FilePath -> Entries e -> Entries (Either e TarBombError) -- | An error that occurs if a tar file is a "tar bomb" that would extract -- files outside of the intended directory. data TarBombError TarBombError :: FilePath -> TarBombError -- | This function checks a sequence of tar entries for a number of -- portability issues. It will complain if: -- -- checkPortability :: Entries e -> Entries (Either e PortabilityError) -- | Portability problems in a tar archive data PortabilityError NonPortableFormat :: Format -> PortabilityError NonPortableFileType :: PortabilityError NonPortableEntryNameChar :: FilePath -> PortabilityError NonPortableFileName :: PortabilityPlatform -> FileNameError -> PortabilityError -- | The name of a platform that portability issues arise from type PortabilityPlatform = String instance Typeable FileNameError instance Typeable TarBombError instance Typeable PortabilityError instance Show PortabilityError instance Exception PortabilityError instance Show TarBombError instance Exception TarBombError instance Exception FileNameError instance Show FileNameError -- | Types and functions to manipulate tar entries. -- -- While the Codec.Archive.Tar module provides only the simple -- high level API, this module provides full access to the details of tar -- entries. This lets you inspect all the meta-data, construct entries -- and handle error cases more precisely. -- -- This module uses common names and so is designed to be imported -- qualified: -- -- 
--   import qualified Codec.Archive.Tar       as Tar
--   import qualified Codec.Archive.Tar.Entry as Tar
--
module Codec.Archive.Tar.Entry -- | Tar archive entry. data Entry Entry :: !TarPath -> !EntryContent -> !Permissions -> !Ownership -> !EpochTime -> !Format -> Entry -- | The path of the file or directory within the archive. This is in a -- tar-specific form. Use entryPath to get a native -- FilePath. entryTarPath :: Entry -> !TarPath -- | The real content of the entry. For NormalFile this includes the -- file data. An entry usually contains a NormalFile or a -- Directory. entryContent :: Entry -> !EntryContent -- | File permissions (Unix style file mode). entryPermissions :: Entry -> !Permissions -- | The user and group to which this file belongs. entryOwnership :: Entry -> !Ownership -- | The time the file was last modified. entryTime :: Entry -> !EpochTime -- | The tar format the archive is using. entryFormat :: Entry -> !Format -- | Native FilePath of the file or directory within the archive. entryPath :: Entry -> FilePath -- | The content of a tar archive entry, which depends on the type of -- entry. -- -- Portable archives should contain only NormalFile and -- Directory. data EntryContent NormalFile :: ByteString -> !FileSize -> EntryContent Directory :: EntryContent SymbolicLink :: !LinkTarget -> EntryContent HardLink :: !LinkTarget -> EntryContent CharacterDevice :: !DevMajor -> !DevMinor -> EntryContent BlockDevice :: !DevMajor -> !DevMinor -> EntryContent NamedPipe :: EntryContent OtherEntryType :: !TypeCode -> ByteString -> !FileSize -> EntryContent data Ownership Ownership :: String -> String -> !Int -> !Int -> Ownership -- | The owner user name. Should be set to "" if unknown. ownerName :: Ownership -> String -- | The owner group name. Should be set to "" if unknown. groupName :: Ownership -> String -- | Numeric owner user id. Should be set to 0 if unknown. ownerId :: Ownership -> !Int -- | Numeric owner group id. Should be set to 0 if unknown. groupId :: Ownership -> !Int type FileSize = Int64 type Permissions = FileMode -- | The number of seconds since the UNIX epoch type EpochTime = Int64 type DevMajor = Int type DevMinor = Int type TypeCode = Char -- | There have been a number of extensions to the tar file format over the -- years. They all share the basic entry fields and put more meta-data in -- different extended headers. data Format -- | This is the classic Unix V7 tar format. It does not support owner and -- group names, just numeric Ids. It also does not support device -- numbers. V7Format :: Format -- | The "USTAR" format is an extension of the classic V7 format. It was -- later standardised by POSIX. It has some restrictions but is the most -- portable format. UstarFormat :: Format -- | The GNU tar implementation also extends the classic V7 format, though -- in a slightly different way from the USTAR format. In general for new -- archives the standard USTAR/POSIX should be used. GnuFormat :: Format -- | An Entry with all default values except for the file name and -- type. It uses the portable USTAR/POSIX format (see -- UstarHeader). -- -- You can use this as a basis and override specific fields, eg: -- -- 
--   (emptyEntry name HardLink) { linkTarget = target }
--
simpleEntry :: TarPath -> EntryContent -> Entry -- | A tar Entry for a file. -- -- Entry fields such as file permissions and ownership have default -- values. -- -- You can use this as a basis and override specific fields. For example -- if you need an executable file you could use: -- -- 
--   (fileEntry name content) { fileMode = executableFileMode }
--
fileEntry :: TarPath -> ByteString -> Entry -- | A tar Entry for a directory. -- -- Entry fields such as file permissions and ownership have default -- values. directoryEntry :: TarPath -> Entry -- | rw-r--r-- for normal files ordinaryFilePermissions :: Permissions -- | rwxr-xr-x for executable files executableFilePermissions :: Permissions -- | rwxr-xr-x for directories directoryPermissions :: Permissions -- | Construct a tar Entry based on a local file. -- -- This sets the entry size, the data contained in the file and the -- file's modification time. If the file is executable then that -- information is also preserved. File ownership and detailed permissions -- are not preserved. -- -- packFileEntry :: FilePath -> TarPath -> IO Entry -- | Construct a tar Entry based on a local directory (but not its -- contents). -- -- The only attribute of the directory that is used is its modification -- time. Directory ownership and detailed permissions are not preserved. packDirectoryEntry :: FilePath -> TarPath -> IO Entry -- | This is a utility function, much like getDirectoryContents. The -- difference is that it includes the contents of subdirectories. -- -- The paths returned are all relative to the top directory. Directory -- paths are distinguishable by having a trailing path separator (see -- hasTrailingPathSeparator). -- -- All directories are listed before the files that they contain. Amongst -- the contents of a directory, subdirectories are listed after normal -- files. The overall result is that files within a directory will be -- together in a single contiguous group. This tends to improve file -- layout and IO performance when creating or extracting tar archives. -- -- getDirectoryContentsRecursive :: FilePath -> IO [FilePath] -- | The classic tar format allowed just 100 characters for the file name. -- The USTAR format extended this with an extra 155 characters, however -- it uses a complex method of splitting the name between the two -- sections. -- -- Instead of just putting any overflow into the extended area, it uses -- the extended area as a prefix. The aggravating insane bit however is -- that the prefix (if any) must only contain a directory prefix. That is -- the split between the two areas must be on a directory separator -- boundary. So there is no simple calculation to work out if a file name -- is too long. Instead we have to try to find a valid split that makes -- the name fit in the two areas. -- -- The rationale presumably was to make it a bit more compatible with old -- tar programs that only understand the classic format. A classic tar -- would be able to extract the file name and possibly some dir prefix, -- but not the full dir prefix. So the files would end up in the wrong -- place, but that's probably better than ending up with the wrong names -- too. -- -- So it's understandable but rather annoying. -- -- data TarPath -- | Convert a native FilePath to a TarPath. -- -- The conversion may fail if the FilePath is too long. See -- TarPath for a description of the problem with splitting long -- FilePaths. toTarPath :: Bool -> FilePath -> Either String TarPath -- | Convert a TarPath to a native FilePath. -- -- The native FilePath will use the native directory separator but -- it is not otherwise checked for validity or sanity. In particular: -- -- fromTarPath :: TarPath -> FilePath -- | Convert a TarPath to a Unix/Posix FilePath. -- -- The difference compared to fromTarPath is that it always -- returns a Unix style path irrespective of the current operating -- system. -- -- This is useful to check how a TarPath would be interpreted on a -- specific operating system, eg to perform portability checks. fromTarPathToPosixPath :: TarPath -> FilePath -- | Convert a TarPath to a Windows FilePath. -- -- The only difference compared to fromTarPath is that it always -- returns a Windows style path irrespective of the current operating -- system. -- -- This is useful to check how a TarPath would be interpreted on a -- specific operating system, eg to perform portability checks. fromTarPathToWindowsPath :: TarPath -> FilePath -- | The tar format allows just 100 ASCII characters for the -- SymbolicLink and HardLink entry types. data LinkTarget -- | Convert a native FilePath to a tar LinkTarget. This may -- fail if the string is longer than 100 characters or if it contains -- non-portable characters. toLinkTarget :: FilePath -> Maybe LinkTarget -- | Convert a tar LinkTarget to a native FilePath. fromLinkTarget :: LinkTarget -> FilePath -- | Convert a tar LinkTarget to a Unix/Posix FilePath. fromLinkTargetToPosixPath :: LinkTarget -> FilePath -- | Convert a tar LinkTarget to a Windows FilePath. fromLinkTargetToWindowsPath :: LinkTarget -> FilePath -- | Reading, writing and manipulating ".tar" archive files. -- -- This module uses common names and so is designed to be imported -- qualified: -- -- 
--   import qualified Codec.Archive.Tar as Tar
--
module Codec.Archive.Tar -- | Create a new ".tar" file from a directory of files. -- -- It is equivalent to calling the standard tar program like so: -- -- 
--   $ tar -f tarball.tar -C base -c dir
--
-- -- This assumes a directory ./base/dir with files inside, eg -- ./base/dir/foo.txt. The file names inside the resulting tar -- file will be relative to dir, eg dir/foo.txt. -- -- This is a high level "all in one" operation. Since you may need -- variations on this function it is instructive to see how it is -- written. It is just: -- -- 
--   BS.writeFile tar . Tar.write =<< Tar.pack base paths
--
-- -- Notes: -- -- The files and directories must not change during this operation or the -- result is not well defined. -- -- The intention of this function is to create tarballs that are portable -- between systems. It is not suitable for doing file system -- backups because file ownership and permissions are not fully -- preserved. File ownership is not preserved at all. File permissions -- are set to simple portable values: -- -- create :: FilePath -> FilePath -> [FilePath] -> IO () -- | Extract all the files contained in a ".tar" file. -- -- It is equivalent to calling the standard tar program like so: -- -- 
--   $ tar -x -f tarball.tar -C dir
--
-- -- So for example if the tarball.tar file contains -- foo/bar.txt then this will extract it to -- dir/foo/bar.txt. -- -- This is a high level "all in one" operation. Since you may need -- variations on this function it is instructive to see how it is -- written. It is just: -- -- 
--   Tar.unpack dir . Tar.read =<< BS.readFile tar
--
-- -- Notes: -- -- Extracting can fail for a number of reasons. The tarball may be -- incorrectly formatted. There may be IO or permission errors. In such -- cases an exception will be thrown and extraction will not continue. -- -- Since the extraction may fail part way through it is not atomic. For -- this reason you may want to extract into an empty directory and, if -- the extraction fails, recursively delete the directory. -- -- Security: only files inside the target directory will be written. -- Tarballs containing entries that point outside of the tarball (either -- absolute paths or relative paths) will be caught and an exception will -- be thrown. extract :: FilePath -> FilePath -> IO () -- | Append new entries to a ".tar" file from a directory of -- files. -- -- This is much like create, except that all the entries are added -- to the end of an existing tar file. Or if the file does not already -- exists then it behaves the same as create. append :: FilePath -> FilePath -> [FilePath] -> IO () -- | Convert a data stream in the tar file format into an internal data -- structure. Decoding errors are reported by the Fail constructor -- of the Entries type. -- -- read :: ByteString -> Entries FormatError -- | Create the external representation of a tar archive by serialising a -- list of tar entries. -- -- write :: [Entry] -> ByteString -- | Creates a tar archive from a list of directory or files. Any -- directories specified will have their contents included recursively. -- Paths in the archive will be relative to the given base directory. -- -- This is a portable implementation of packing suitable for portable -- archives. In particular it only constructs NormalFile and -- Directory entries. Hard links and symbolic links are treated -- like ordinary files. It cannot be used to pack directories containing -- recursive symbolic links. Special files like FIFOs (named pipes), -- sockets or device files will also cause problems. -- -- An exception will be thrown for any file names that are too long to -- represent as a TarPath. -- -- pack :: FilePath -> [FilePath] -> IO [Entry] -- | Create local files and directories based on the entries of a tar -- archive. -- -- This is a portable implementation of unpacking suitable for portable -- archives. It handles NormalFile and Directory entries -- and has simulated support for SymbolicLink and HardLink -- entries. Links are implemented by copying the target file. This -- therefore works on Windows as well as Unix. All other entry types are -- ignored, that is they are not unpacked and no exception is raised. -- -- If the Entries ends in an error then it is raised an an -- exception. Any files or directories that have been unpacked before the -- error was encountered will not be deleted. For this reason you may -- want to unpack into an empty directory so that you can easily clean up -- if unpacking fails part-way. -- -- On its own, this function only checks for security (using -- checkSecurity). You can do other checks by applying checking -- functions to the Entries that you pass to this function. For -- example: -- -- 
--   unpack dir (checkTarbomb expectedDir entries)
--
-- -- If you care about the priority of the reported errors then you may -- want to use checkSecurity before checkTarbomb or other -- checks. unpack :: Exception e => FilePath -> Entries e -> IO () -- | Tar archive entry. data Entry -- | Native FilePath of the file or directory within the archive. entryPath :: Entry -> FilePath -- | The real content of the entry. For NormalFile this includes the -- file data. An entry usually contains a NormalFile or a -- Directory. entryContent :: Entry -> EntryContent -- | The content of a tar archive entry, which depends on the type of -- entry. -- -- Portable archives should contain only NormalFile and -- Directory. data EntryContent NormalFile :: ByteString -> !FileSize -> EntryContent Directory :: EntryContent SymbolicLink :: !LinkTarget -> EntryContent HardLink :: !LinkTarget -> EntryContent CharacterDevice :: !DevMajor -> !DevMinor -> EntryContent BlockDevice :: !DevMajor -> !DevMinor -> EntryContent NamedPipe :: EntryContent OtherEntryType :: !TypeCode -> ByteString -> !FileSize -> EntryContent -- | A tar archive is a sequence of entries. -- -- The point of this type as opposed to just using a list is that it -- makes the failure case explicit. We need this because the sequence of -- entries we get from reading a tarball can include errors. -- -- It is a concrete data type so you can manipulate it directly but it is -- often clearer to use the provided functions for mapping, folding and -- unfolding. -- -- Converting from a list can be done with just foldr Next Done. -- Converting back into a list can be done with foldEntries -- however in that case you must be prepared to handle the Fail -- case inherent in the Entries type. -- -- The Monoid instance lets you concatenate archives or append -- entries to an archive. data Entries e Next :: Entry -> (Entries e) -> Entries e Done :: Entries e Fail :: e -> Entries e -- | This is like the standard map function on lists, but for -- Entries. It includes failure as a extra possible outcome of the -- mapping function. -- -- If your mapping function cannot fail it may be more convenient to use -- mapEntriesNoFail mapEntries :: (Entry -> Either e' Entry) -> Entries e -> Entries (Either e e') -- | Like mapEntries but the mapping function itself cannot fail. mapEntriesNoFail :: (Entry -> Entry) -> Entries e -> Entries e -- | This is like the standard foldr function on lists, but for -- Entries. Compared to foldr it takes an extra function to -- account for the possibility of failure. -- -- This is used to consume a sequence of entries. For example it could be -- used to scan a tarball for problems or to collect an index of the -- contents. foldEntries :: (Entry -> a -> a) -> a -> (e -> a) -> Entries e -> a -- | This is like the standard unfoldr function on lists, but for -- Entries. It includes failure as an extra possibility that the -- stepper function may return. -- -- It can be used to generate Entries from some other type. For -- example it is used internally to lazily unfold entries from a -- ByteString. unfoldEntries :: (a -> Either e (Maybe (Entry, a))) -> a -> Entries e -- | Errors that can be encountered when parsing a Tar archive. data FormatError TruncatedArchive :: FormatError ShortTrailer :: FormatError BadTrailer :: FormatError TrailingJunk :: FormatError ChecksumIncorrect :: FormatError NotTarFormat :: FormatError UnrecognisedTarFormat :: FormatError HeaderBadNumericEncoding :: FormatError