aboutsummaryrefslogblamecommitdiffstats
path: root/lib/stdlib/doc/src/erl_tar.xml
blob: 95eefb8f9be3b2f8af21f0b4278fbfa203207755 (plain) (tree)
1
2
3
4
5
6
7
                                       




                                     
                                        





























                                                                                        




                                                                       

























                                                                              













                                                                                     





                                                                                                                                                                                                                                                                                                                                                   


















                                                                           

                                                              



                                                      

                                                                   












                                                                                





                                                                                    







                                                                                         
                                                  
                                    






















                                                                        

                                                                  










                                                                                        

                                                  

             

                                                                      














                                                                                        

                                                  

             
                                                                      











































                                                                                       

                                                                        


























                                                                                

                                                                        




































































                                                                                          

                                                                         














                                                                            

                                                                        































                                                                                       


                  






























































































                                                                                                                                                         








                                                                       

                                                                           








                                                                                   

                                                                           








                                                                    
                                                                             










                                                                                 

                                                                     






                                                                    
<?xml version="1.0" encoding="utf-8" ?>
<!DOCTYPE erlref SYSTEM "erlref.dtd">

<erlref>
  <header>
    <copyright>
      <year>2003</year><year>2013</year>
      <holder>Ericsson AB. All Rights Reserved.</holder>
    </copyright>
    <legalnotice>
      The contents of this file are subject to the Erlang Public License,
      Version 1.1, (the "License"); you may not use this file except in
      compliance with the License. You should have received a copy of the
      Erlang Public License along with this software. If not, it can be
      retrieved online at http://www.erlang.org/.
    
      Software distributed under the License is distributed on an "AS IS"
      basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See
      the License for the specific language governing rights and limitations
      under the License.
    
    </legalnotice>

    <title>erl_tar</title>
    <prepared>Bjorn Gustavsson</prepared>
    <responsible>Bjorn Gustavsson</responsible>
    <docno>1</docno>
    <approved>Kenneth Lundin</approved>
    <checked></checked>
    <date>03-01-21</date>
    <rev>A</rev>
    <file>erl_tar.sgml</file>
  </header>
  <module>erl_tar</module>
  <modulesummary>Unix 'tar' utility for reading and writing tar archives</modulesummary>
  <description>
    <p>The <c>erl_tar</c> module archives and extract files to and from
      a tar file. <c>erl_tar</c> supports the <c>ustar</c> format
      (IEEE Std 1003.1 and ISO/IEC&nbsp;9945-1). All modern <c>tar</c>
      programs (including GNU tar) can read this format. To ensure that
      that GNU tar produces a tar file that <c>erl_tar</c> can read,
      give the <c>--format=ustar</c> option to GNU tar.</p>
    <p>By convention, the name of a tar file should end in "<c>.tar</c>".
      To abide to the convention, you'll need to add "<c>.tar</c>" yourself
      to the name.</p>
    <p>Tar files can be created in one operation using the
      <seealso marker="#create_2">create/2</seealso> or
      <seealso marker="#create_3">create/3</seealso> function.</p>
    <p>Alternatively, for more control, the
      <seealso marker="#open">open</seealso>,
      <seealso marker="#add">add/3,4</seealso>, and 
      <seealso marker="#close">close/1</seealso> functions can be used.</p>
    <p>To extract all files from a tar file, use the 
      <seealso marker="#extract_1">extract/1</seealso> function.
      To extract only some files or to be able to specify some more options,
      use the <seealso marker="#extract_2">extract/2</seealso> function.</p>
    <p>To return a list of the files in a tar file,
      use either the <seealso marker="#table_1">table/1</seealso> or
      <seealso marker="#table_2">table/2</seealso> function.
      To print a list of files to the Erlang shell,
      use either the <seealso marker="#t_1">t/1</seealso> or
      <seealso marker="#tt_1">tt/1</seealso> function.</p>
    <p>To convert an error term returned from one of the functions
      above to a readable message, use the
      <seealso marker="#format_error_1">format_error/1</seealso> function.</p>
  </description>

  <section>
    <title>UNICODE SUPPORT</title>
    <p>If <seealso
    marker="kernel:file#native_name_encoding/0">file:native_name_encoding/0</seealso>
    returns <c>utf8</c>, path names will be encoded in UTF-8 when
    creating tar files and path names will be assumed to be encoded in
    UTF-8 when extracting tar files.</p>

    <p>If <seealso
    marker="kernel:file#native_name_encoding/0">file:native_name_encoding/0</seealso>
    returns <c>latin1</c>, no translation of path names will be
    done.</p>
  </section>

  <section>
    <title>OTHER STORAGE MEDIA</title>
    <p>The <c>erl_ftp</c> module normally accesses the tar-file on disk using the <seealso marker="kernel:file">file module</seealso>.  When other needs arise, there is a way to define your own low-level Erlang functions to perform the writing and reading on the storage media. See <seealso marker="#init/3">init/3</seealso> for usage.</p>
    <p>An example of this is the sftp support in <seealso marker="ssh:ssh_sftp#open_tar/3">ssh_sftp:open_tar/3</seealso>. That function opens a tar file on a remote machine using an sftp channel.</p>
  </section>

  <section>
    <title>LIMITATIONS</title>
    <p>For maximum compatibility, it is safe to archive files with names
      up to 100 characters in length. Such tar files can generally be
      extracted by any <c>tar</c> program.</p>
    <p>If filenames exceed 100 characters in length, the resulting tar
      file can only be correctly extracted by a POSIX-compatible <c>tar</c>
      program (such as Solaris <c>tar</c>), not by GNU tar.</p>
    <p>File have longer names than 256 bytes cannot be stored at all.</p>
    <p>The filename of the file a symbolic link points is always limited
      to 100 characters.</p>
  </section>
  <funcs>
    <func>
      <name>add(TarDescriptor, Filename, Options) -> RetValue</name>
      <fsummary>Add a file to an open tar file</fsummary>
      <type>
        <v>TarDescriptor = term()</v>
        <v>Filename = filename()</v>
        <v>Options = [Option]</v>
        <v>Option = dereference|verbose|{chunks,ChunkSize}</v>
	<v>ChunkSize = positive_integer()</v>
        <v>RetValue = ok|{error,{Filename,Reason}}</v>
        <v>Reason = term()</v>
      </type>
      <desc>
        <p>The <marker id="add"></marker><c>add/3</c> function adds
           a file to a tar file that has been opened for writing by
          <seealso marker="#open">open/1</seealso>.</p>
        <taglist>
          <tag><c>dereference</c></tag>
          <item>
            <p>By default, symbolic links will be stored as symbolic links
              in the tar file. Use the <c>dereference</c> option to override the
              default and store the file that the symbolic link points to into
              the tar file.</p>
          </item>
          <tag><c>verbose</c></tag>
          <item>
            <p>Print an informational message about the file being added.</p>
          </item>
	  <tag><c>{chunks,ChunkSize}</c></tag>
	  <item>
	    <p>Read data in parts from the file. This is intended for memory-limited
	    machines that for example builds a tar file on a remote machine over
	    <seealso marker="ssh:ssh_sftp#open_tar/3">sftp</seealso>.</p>
	  </item>
        </taglist>
      </desc>
    </func>
    <func>
      <name>add(TarDescriptor, FilenameOrBin, NameInArchive, Options) -> RetValue </name>
      <fsummary>Add a file to an open tar file</fsummary>
      <type>
        <v>TarDescriptor = term()</v>
        <v>FilenameOrBin = filename()|binary()</v>
        <v>Filename = filename()</v>
        <v>NameInArchive = filename()</v>
        <v>Options = [Option]</v>
        <v>Option = dereference|verbose</v>
        <v>RetValue = ok|{error,{Filename,Reason}}</v>
        <v>Reason = term()</v>
      </type>
      <desc>
        <p>The <c>add/4</c> function adds a file to a tar file
          that has been opened for writing by
          <seealso marker="#open">open/1</seealso>. It accepts the same
          options as <seealso marker="#add">add/3</seealso>.</p>
        <p><c>NameInArchive</c> is the name under which the file will
          be stored in the tar file. That is the name that the file will
          get when it will be extracted from the tar file.</p>
      </desc>
    </func>
    <func>
      <name>close(TarDescriptor)</name>
      <fsummary>Close an open tar file</fsummary>
      <type>
        <v>TarDescriptor = term()</v>
      </type>
      <desc>
        <p>The <marker id="close"></marker><c>close/1</c> function
          closes a tar file
          opened by <seealso marker="#open">open/1</seealso>.</p>
      </desc>
    </func>
    <func>
      <name>create(Name, FileList) ->RetValue </name>
      <fsummary>Create a tar archive</fsummary>
      <type>
        <v>Name = filename()</v>
        <v>FileList = [Filename|{NameInArchive, binary()},{NameInArchive, Filename}]</v>
        <v>Filename = filename()</v>
        <v>NameInArchive = filename()</v>
        <v>RetValue = ok|{error,{Name,Reason}}</v>
        <v>Reason = term()</v>
      </type>
      <desc>
        <p>The <marker id="create_2"></marker><c>create/2</c> function
          creates a tar file and
          archives the files whose names are given in <c>FileList</c> into it.
          The files may either be read from disk or given as
          binaries.</p>
      </desc>
    </func>
    <func>
      <name>create(Name, FileList, OptionList)</name>
      <fsummary>Create a tar archive with options</fsummary>
      <type>
        <v>Name = filename()</v>
	<v>FileList = [Filename|{NameInArchive, binary()},{NameInArchive, Filename}]</v>
	<v>Filename = filename()</v>
        <v>NameInArchive = filename()</v>
        <v>OptionList = [Option]</v>
        <v>Option = compressed|cooked|dereference|verbose</v>
        <v>RetValue = ok|{error,{Name,Reason}}</v>
        <v>Reason = term()</v>
      </type>
      <desc>
        <p>The <marker id="create_3"></marker><c>create/3</c> function
          creates a tar file and archives the files whose names are given
          in <c>FileList</c> into it. The files may either be read from
          disk or given as binaries.</p>
        <p>The options in <c>OptionList</c> modify the defaults as follows.
          </p>
        <taglist>
          <tag><c>compressed</c></tag>
          <item>
            <p>The entire tar file will be compressed, as if it has
              been run through the <c>gzip</c> program. To abide to the
              convention that a compressed tar file should end in "<c>.tar.gz</c>" or
              "<c>.tgz</c>", you'll need to add the appropriate extension yourself.</p>
          </item>
          <tag><c>cooked</c></tag>
          <item>
            <p>By default, the <c>open/2</c> function will open the tar file
              in <c>raw</c> mode, which is faster but does not allow a remote (erlang)
              file server to be used. Adding <c>cooked</c> to the mode list will 
              override the default and open the tar file without the <c>raw</c>
              option.</p>
          </item>
          <tag><c>dereference</c></tag>
          <item>
            <p>By default, symbolic links will be stored as symbolic links
              in the tar file. Use the <c>dereference</c> option to override the
              default and store the file that the symbolic link points to into
              the tar file.</p>
          </item>
          <tag><c>verbose</c></tag>
          <item>
            <p>Print an informational message about each file being added.</p>
          </item>
        </taglist>
      </desc>
    </func>
    <func>
      <name>extract(Name) -> RetValue</name>
      <fsummary>Extract all files from a tar file</fsummary>
      <type>
        <v>Name = filename()</v>
        <v>RetValue = ok|{error,{Name,Reason}}</v>
        <v>Reason = term()</v>
      </type>
      <desc>
        <p>The <marker id="extract_1"></marker><c>extract/1</c> function
          extracts all files from a tar archive.</p>
        <p>If the <c>Name</c> argument is given as "<c>{binary,Binary}</c>",
          the contents of the binary is assumed to be a tar archive.
          </p>
        <p>If the <c>Name</c> argument is given as "<c>{file,Fd}</c>",
          <c>Fd</c> is assumed to be a file descriptor returned from
          the <c>file:open/2</c> function.
          </p>
        <p>Otherwise, <c>Name</c> should be a filename.</p>
      </desc>
    </func>
    <func>
      <name>extract(Name, OptionList)</name>
      <fsummary>Extract files from a tar file</fsummary>
      <type>
        <v>Name = filename() | {binary,Binary} | {file,Fd}  </v>
        <v>Binary = binary()</v>
        <v>Fd = file_descriptor()</v>
        <v>OptionList = [Option]</v>
        <v>Option = {cwd,Cwd}|{files,FileList}|keep_old_files|verbose|memory</v>
        <v>Cwd = [dirname()]</v>
        <v>FileList = [filename()]</v>
        <v>RetValue = ok|MemoryRetValue|{error,{Name,Reason}}</v>
        <v>MemoryRetValue = {ok, [{NameInArchive,binary()}]}</v>
        <v>NameInArchive = filename()</v>
        <v>Reason = term()</v>
      </type>
      <desc>
        <p>The <marker id="extract_2"></marker><c>extract/2</c> function
          extracts files from a tar archive.</p>
        <p>If the <c>Name</c> argument is given as "<c>{binary,Binary}</c>",
          the contents of the binary is assumed to be a tar archive.
          </p>
        <p>If the <c>Name</c> argument is given as "<c>{file,Fd}</c>",
          <c>Fd</c> is assumed to be a file descriptor returned from
          the <c>file:open/2</c> function.
          </p>
        <p>Otherwise, <c>Name</c> should be a filename.
          </p>
        <p>The following options modify the defaults for the extraction as
          follows.</p>
        <taglist>
          <tag><c>{cwd,Cwd}</c></tag>
          <item>
            <p>Files with relative filenames will by default be extracted
              to the current working directory.
              Given the <c>{cwd,Cwd}</c> option, the <c>extract/2</c> function
              will extract into the directory <c>Cwd</c> instead of to the current
              working directory.</p>
          </item>
          <tag><c>{files,FileList}</c></tag>
          <item>
            <p>By default, all files will be extracted from the tar file.
              Given the <c>{files,Files}</c> option, the <c>extract/2</c> function
              will only extract the files whose names are included in <c>FileList</c>.</p>
          </item>
          <tag><c>compressed</c></tag>
          <item>
            <p>Given the <c>compressed</c> option, the <c>extract/2</c>
              function will uncompress the file while extracting
              If the tar file is not actually compressed, the <c>compressed</c>
              will effectively be ignored.</p>
          </item>
          <tag><c>cooked</c></tag>
          <item>
            <p>By default, the <c>open/2</c> function will open the tar file
              in <c>raw</c> mode, which is faster but does not allow a remote (erlang)
              file server to be used. Adding <c>cooked</c> to the mode list will 
              override the default and open the tar file without the <c>raw</c>
              option.</p>
          </item>
          <tag><c>memory</c></tag>
          <item>
            <p>Instead of extracting to a directory, the memory option will
	      give the result  as  a  list  of  tuples  {Filename, Binary}, where
	      Binary is a binary containing the extracted data of the file named
	      Filename in the tar file.</p>
          </item>
          <tag><c>keep_old_files</c></tag>
          <item>
            <p>By default, all existing files with the same name as file in
              the tar file will be overwritten
              Given the <c>keep_old_files</c> option, the <c>extract/2</c> function
              will not overwrite any existing files.</p>
          </item>
          <tag><c>verbose</c></tag>
          <item>
            <p>Print an informational message as each file is being extracted.</p>
          </item>
        </taglist>
      </desc>
    </func>
    <func>
      <name>format_error(Reason) -> string()</name>
      <fsummary>Convert error term to a readable string</fsummary>
      <type>
        <v>Reason = term()</v>
      </type>
      <desc>
        <p>The <marker id="format_error_1"></marker><c>format_error/1</c>
          function converts
          an error reason term to a human-readable error message string.</p>
      </desc>
    </func>
    <func>
      <name>open(Name, OpenModeList) -> RetValue</name>
      <fsummary>Open a tar file for writing.</fsummary>
      <type>
        <v>Name = filename()</v>
        <v>OpenModeList = [OpenMode]</v>
        <v>Mode = write|compressed|cooked</v>
        <v>RetValue = {ok,TarDescriptor}|{error,{Name,Reason}}</v>
	<v>TarDescriptor = term()</v>
        <v>Reason = term()</v>
      </type>
      <desc>
        <p>The <marker id="open"></marker><c>open/2</c> function creates
         a tar file for writing.
        (Any existing file with the same name will be truncated.)</p>
        <p>By convention, the name of a tar file should end in "<c>.tar</c>".
          To abide to the convention, you'll need to add "<c>.tar</c>" yourself
          to the name.</p>
        <p>Except for the <c>write</c> atom the following atoms
	may be added to <c>OpenModeList</c>:</p>
        <taglist>
          <tag><c>compressed</c></tag>
          <item>
            <p>The entire tar file will be compressed, as if it has
              been run through the <c>gzip</c> program. To abide to the
              convention that a compressed tar file should end in "<c>.tar.gz</c>" or
              "<c>.tgz</c>", you'll need to add the appropriate extension yourself.</p>
          </item>
          <tag><c>cooked</c></tag>
          <item>
            <p>By default, the <c>open/2</c> function will open the tar file
              in <c>raw</c> mode, which is faster but does not allow a remote (erlang)
              file server to be used. Adding <c>cooked</c> to the mode list will 
              override the default and open the tar file without the <c>raw</c>
              option.</p>
          </item>
        </taglist>
        <p>Use the <seealso marker="#add">add/3,4</seealso> functions
          to add one file at the time into an opened tar file. When you are
          finished adding files, use the <seealso marker="#close">close</seealso>
          function to close the tar file.</p>
        <warning>
          <p>The <c>TarDescriptor</c> term is not a file descriptor.
            You should not rely on the specific contents of the <c>TarDescriptor</c>
            term, as it may change in future versions as more features are added
            to the <c>erl_tar</c> module.</p>
        </warning>
      </desc>
    </func>

    <func>
      <name>init(UserPrivate, AccessMode, Fun) -> {ok,TarDescriptor} | {error,Reason}
</name>
      <fsummary>Creates a TarDescriptor used in subsequent tar operations when
      defining own low-level storage access functions
      </fsummary>
      <type>
	<v>UserPrivate = term()</v>
	<v>AccessMode = [write] | [read]</v>
	<v>Fun when AccessMode is [write] = fun(write,   {UserPrivate,DataToWrite})->...;
	                                       (position,{UserPrivate,Position})->...;
	                                       (close,   UserPrivate)->...
					    end
        </v>
	<v>Fun when AccessMode is [read] = fun(read2,   {UserPrivate,Size})->...;
	                                      (position,{UserPrivate,Position})->...;
	                                      (close,   UserPrivate)->...
					    end
        </v>
	<v>TarDescriptor = term()</v>
	<v>Reason = term()</v>
      </type>
      <desc>
	<p>The <c>Fun</c> is the definition of what to do when the different
	storage operations functions are to be called from the higher tar
	handling functions (<c>add/3</c>, <c>add/4</c>, <c>close/1</c>...).
	</p>
	<p>The <c>Fun</c> will be called when the tar function wants to do
	a low-level operation, like writing a block to a file.  The Fun is called
	as <c>Fun(Op,{UserPrivate,Parameters...})</c> where <c>Op</c> is the operation name,
	<c>UserPrivate</c> is the term passed as the first argument to <c>init/1</c> and
	<c>Parameters...</c> are the data added by the tar function to be passed down to
	the storage handling function.
	</p>
	<p>The parameter <c>UserPrivate</c> is typically the result of opening a low level
	structure like a file descriptor, a sftp channel id or such.  The different <c>Fun</c>
	clauses operates on that very term.
	</p>
	<p>The fun clauses parameter lists are:
	<taglist>
	  <tag><c>(write, {UserPrivate,DataToWrite})</c></tag>
	  <item>Write the term <c>DataToWrite</c> using <c>UserPrivate</c></item>
	  <tag><c>(close, UserPrivate)</c></tag>
	  <item>Close the access.</item>
	  <tag><c>(read2, {UserPrivate,Size})</c></tag>
	  <item>Read using <c>UserPrivate</c> but only <c>Size</c> bytes. Note that there is
	  only an arity-2 read function, not an arity-1
	  </item>
	  <tag><c> (position,{UserPrivate,Position})</c></tag>
	  <item>Sets the position of <c>UserPrivate</c> as defined for files in <seealso marker="kernel:file#position-2">file:position/2</seealso></item>
	  <tag><c></c></tag>
	  <item></item>
	</taglist>
	</p>
	<p>A complete <c>Fun</c> parameter for reading and writing on files using the
	<seealso marker="kernel:file">file module</seealso> could be:
	</p>
	<code type="none">
	  ExampleFun = 
	     fun(write, {Fd,Data}) ->  file:write(Fd, Data);
	        (position, {Fd,Pos}) -> file:position(Fd, Pos);
	        (read2, {Fd,Size}) -> file:read(Fd,Size);
	        (close, Fd) -> file:close(Fd)
	     end
	</code>
	<p>where <c>Fd</c> was given to the <c>init/3</c> function as:</p>
	<code>
	  {ok,Fd} = file:open(Name,...).
	  {ok,TarDesc} = erl_tar:init(Fd, [write], ExampleFun),
	</code>
	<p>The <c>TarDesc</c> is then used:</p>
	<code>
	  erl_tar:add(TarDesc, SomeValueIwantToAdd, FileNameInTarFile),
	  ....,
	  erl_tar:close(TarDesc)
	</code>
	<p>When the erl_tar core wants to e.g. write a piece of Data, it would call
	<c>ExampleFun(write,{UserPrivate,Data})</c>.
	</p>
	<note>
	  <p>The example above with <c>file</c> module operations is not necessary to
	  use directly since that is what the <seealso marker="#open">open</seealso> function
	  in principle does.
	  </p>
	</note>
        <warning>
          <p>The <c>TarDescriptor</c> term is not a file descriptor.
            You should not rely on the specific contents of the <c>TarDescriptor</c>
            term, as it may change in future versions as more features are added
            to the <c>erl_tar</c> module.</p>
        </warning>
      </desc>
    </func>

    <func>
      <name>table(Name) -> RetValue</name>
      <fsummary>Retrieve the name of all files in a tar file</fsummary>
      <type>
        <v>Name = filename()</v>
        <v>RetValue = {ok,[string()]}|{error,{Name,Reason}}</v>
        <v>Reason = term()</v>
      </type>
      <desc>
        <p>The <marker id="table_1"></marker><c>table/1</c> function
          retrieves the names of all files in the tar file <c>Name</c>.</p>
      </desc>
    </func>
    <func>
      <name>table(Name, Options)</name>
      <fsummary>Retrieve name and information of all files in a tar file</fsummary>
      <type>
        <v>Name = filename()</v>
      </type>
      <desc>
        <p>The <marker id="table_2"></marker><c>table/2</c> function
          retrieves the names of all files in the tar file <c>Name</c>.</p>
      </desc>
    </func>
    <func>
      <name>t(Name)</name>
      <fsummary>Print the name of each file in a tar file</fsummary>
      <type>
        <v>Name = filename()</v>
      </type>
      <desc>
        <p>The <marker id="t_1"></marker><c>t/1</c> function prints the names
          of all files in the tar file <c>Name</c> to the Erlang shell.
          (Similar to "<c>tar&nbsp;t</c>".)</p>
      </desc>
    </func>
    <func>
      <name>tt(Name)</name>
      <fsummary>Print name and information for each file in a tar file</fsummary>
      <type>
        <v>Name = filename()</v>
      </type>
      <desc>
        <p>The <marker id="tt_1"></marker><c>tt/1</c> function prints
          names and
          information about all files in the tar file <c>Name</c> to
          the Erlang shell. (Similar to "<c>tar&nbsp;tv</c>".)</p>
      </desc>
    </func>
  </funcs>
</erlref>