1%%
2%% %CopyrightBegin%
3%%
4%% Copyright Ericsson AB 1997-2020. All Rights Reserved.
5%%
6%% Licensed under the Apache License, Version 2.0 (the "License");
7%% you may not use this file except in compliance with the License.
8%% You may obtain a copy of the License at
9%%
10%%     http://www.apache.org/licenses/LICENSE-2.0
11%%
12%% Unless required by applicable law or agreed to in writing, software
13%% distributed under the License is distributed on an "AS IS" BASIS,
14%% WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15%% See the License for the specific language governing permissions and
16%% limitations under the License.
17%%
18%% %CopyrightEnd%
19
20%% Options used when adding files to a tar archive.
21-record(add_opts, {
22	 read_info,          %% Fun to use for read file/link info.
23	 chunk_size = 0,     %% For file reading when sending to sftp. 0=do not chunk
24         verbose = false,    %% Verbose on/off.
25         atime = undefined,
26         mtime = undefined,
27         ctime = undefined,
28         uid = 0,
29         gid = 0}).
30-type add_opts() :: #add_opts{}.
31
32%% Options used when reading a tar archive.
33-record(read_opts, {
34          cwd                    :: string(),  %% Current working directory.
35          keep_old_files = false :: boolean(), %% Owerwrite or not.
36          files = all,                         %% Set of files to extract (or all)
37          output = file :: 'file' | 'memory',
38          open_mode = [],                      %% Open mode options.
39          verbose = false :: boolean()}).      %% Verbose on/off.
40-type read_opts() :: #read_opts{}.
41
42-type add_opt() :: dereference |
43                   verbose |
44                   {chunks, pos_integer()} |
45                   {atime, non_neg_integer()} |
46                   {mtime, non_neg_integer()} |
47                   {ctime, non_neg_integer()} |
48                   {uid, non_neg_integer()} |
49                   {gid, non_neg_integer()}.
50
51-type name_in_archive() :: string().
52
53-type extract_opt() :: {cwd, string()} |
54                       {files, [name_in_archive()]} |
55                       compressed |
56                       cooked |
57                       memory |
58                       keep_old_files |
59                       verbose.
60
61-type create_opt() :: compressed |
62                      cooked |
63                      dereference |
64                      verbose.
65
66-type filelist() :: [file:filename() |
67                     {name_in_archive(), file:filename_all()}].
68
69-type tar_time() :: non_neg_integer().
70
71%% The tar header, once fully parsed.
72-record(tar_header, {
73          name = "" :: name_in_archive(),       %% name of header file entry
74          mode = 8#100644 :: non_neg_integer(), %% permission and mode bits
75          uid = 0 :: non_neg_integer(),         %% user id of owner
76          gid = 0 :: non_neg_integer(),         %% group id of owner
77          size = 0 :: non_neg_integer(),        %% length in bytes
78          mtime :: tar_time(),                  %% modified time
79          typeflag :: char(),                   %% type of header entry
80          linkname = "" :: name_in_archive(),   %% target name of link
81          uname = "" :: string(),               %% user name of owner
82          gname = "" :: string(),               %% group name of owner
83          devmajor = 0 :: non_neg_integer(),    %% major number of character or block device
84          devminor = 0 :: non_neg_integer(),    %% minor number of character or block device
85          atime :: tar_time(),                  %% access time
86          ctime :: tar_time()                   %% status change time
87         }).
88-type tar_header() :: #tar_header{}.
89
90%% Metadata for a sparse file fragment
91-record(sparse_entry, {
92         offset = 0 :: non_neg_integer(),
93         num_bytes = 0 :: non_neg_integer()}).
94-type sparse_entry() :: #sparse_entry{}.
95%% Contains metadata about fragments of a sparse file
96-record(sparse_array, {
97          entries = [] :: [sparse_entry()],
98          is_extended = false :: boolean(),
99          max_entries = 0 :: non_neg_integer()}).
100-type sparse_array() :: #sparse_array{}.
101%% A subset of tar header fields common to all tar implementations
102-record(header_v7, {
103          name :: binary(),
104          mode :: binary(), %% octal
105          uid :: binary(), %% integer
106          gid :: binary(), %% integer
107          size :: binary(), %% integer
108          mtime :: binary(), %% integer
109          checksum :: binary(), %% integer
110          typeflag :: byte(), %% char
111          linkname :: binary()}).
112-type header_v7() :: #header_v7{}.
113%% The set of fields specific to GNU tar formatted archives
114-record(header_gnu, {
115          header_v7 :: header_v7(),
116          magic :: binary(),
117          version :: binary(),
118          uname :: binary(),
119          gname :: binary(),
120          devmajor :: binary(), %% integer
121          devminor :: binary(), %% integer
122          atime :: binary(), %% integer
123          ctime :: binary(), %% integer
124          sparse :: sparse_array(),
125          real_size :: binary()}). %% integer
126-type header_gnu() :: #header_gnu{}.
127%% The set of fields specific to STAR-formatted archives
128-record(header_star, {
129          header_v7 :: header_v7(),
130          magic :: binary(),
131          version :: binary(),
132          uname :: binary(),
133          gname :: binary(),
134          devmajor :: binary(), %% integer
135          devminor :: binary(), %% integer
136          prefix :: binary(),
137          atime :: binary(), %% integer
138          ctime :: binary(), %% integer
139          trailer :: binary()}).
140-type header_star() :: #header_star{}.
141%% The set of fields specific to USTAR-formatted archives
142-record(header_ustar, {
143          header_v7 :: header_v7(),
144          magic :: binary(),
145          version :: binary(),
146          uname :: binary(),
147          gname :: binary(),
148          devmajor :: binary(), %% integer
149          devminor :: binary(), %% integer
150          prefix :: binary()}).
151-type header_ustar() :: #header_ustar{}.
152
153-type header_fields() :: header_v7() |
154                         header_gnu() |
155                         header_star() |
156                         header_ustar().
157
158%% The overall tar reader, it holds the low-level file handle,
159%% its access, position, and the I/O primitives wrapper.
160-record(reader, {
161          handle :: user_data(),
162          access :: read | write | ram,
163          pos = 0 :: non_neg_integer(),
164          func :: file_op()
165         }).
166-opaque tar_descriptor() :: #reader{}.
167-export_type([tar_descriptor/0]).
168
169%% A reader for a regular file within the tar archive,
170%% It tracks its current state relative to that file.
171-record(reg_file_reader, {
172          handle :: tar_descriptor(),
173          num_bytes = 0,
174          pos = 0,
175          size = 0
176         }).
177-type reg_file_reader() :: #reg_file_reader{}.
178%% A reader for a sparse file within the tar archive,
179%% It tracks its current state relative to that file.
180-record(sparse_file_reader, {
181          handle :: tar_descriptor(),
182          num_bytes = 0, %% bytes remaining
183          pos = 0, %% pos
184          size = 0, %% total size of file
185          sparse_map = #sparse_array{}
186         }).
187-type sparse_file_reader() :: #sparse_file_reader{}.
188
189%% Types for the readers
190-type descriptor_type() :: tar_descriptor() | reg_file_reader() | sparse_file_reader().
191-type user_data() :: term().
192
193%% Type for the I/O primitive wrapper function
194-type file_op() :: fun((write | close | read2 | position,
195                       {user_data(), iodata()} | user_data() | {user_data(), non_neg_integer()}
196                        | {user_data(), non_neg_integer()}) ->
197                              ok | eof | {ok, string() | binary()} | {ok, non_neg_integer()}
198                                 | {error, term()}).
199
200%% These constants (except S_IFMT) are
201%% used to determine what type of device
202%% a file is. Namely, `S_IFMT band file_info.mode`
203%% will equal one of these contants, and tells us
204%% which type it is. The stdlib file_info record
205%% does not differentiate between device types, and
206%% will not allow us to differentiate between sockets
207%% and named pipes. These constants are pulled from libc.
208-define(S_IFMT, 61440).
209-define(S_IFSOCK, 49152). %% socket
210-define(S_FIFO, 4096).    %% fifo/named pipe
211-define(S_IFBLK, 24576).  %% block device
212-define(S_IFCHR, 8192).   %% character device
213
214%% Typeflag constants for the tar header
215-define(TYPE_REGULAR, $0).         %% regular file
216-define(TYPE_REGULAR_A, 0).        %% regular file
217-define(TYPE_LINK, $1).            %% hard link
218-define(TYPE_SYMLINK, $2).         %% symbolic link
219-define(TYPE_CHAR, $3).            %% character device node
220-define(TYPE_BLOCK, $4).           %% block device node
221-define(TYPE_DIR, $5).             %% directory
222-define(TYPE_FIFO, $6).            %% fifo node
223-define(TYPE_CONT, $7).            %% reserved
224-define(TYPE_X_HEADER, $x).        %% extended header
225-define(TYPE_X_GLOBAL_HEADER, $g). %% global extended header
226-define(TYPE_GNU_LONGNAME, $L).    %% next file has a long name
227-define(TYPE_GNU_LONGLINK, $K).    %% next file symlinks to a file with a long name
228-define(TYPE_GNU_SPARSE, $S).      %% sparse file
229
230%% Mode constants from tar spec
231-define(MODE_ISUID, 4000).    %% set uid
232-define(MODE_ISGID, 2000).    %% set gid
233-define(MODE_ISVTX, 1000).    %% save text (sticky bit)
234-define(MODE_ISDIR, 40000).   %% directory
235-define(MODE_ISFIFO, 10000).  %% fifo
236-define(MODE_ISREG, 100000).  %% regular file
237-define(MODE_ISLNK, 120000).  %% symbolic link
238-define(MODE_ISBLK, 60000).   %% block special file
239-define(MODE_ISCHR, 20000).   %% character special file
240-define(MODE_ISSOCK, 140000). %% socket
241
242%% Keywords for PAX extended header
243-define(PAX_ATIME, <<"atime">>).
244-define(PAX_CHARSET, <<"charset">>).
245-define(PAX_COMMENT, <<"comment">>).
246-define(PAX_CTIME, <<"ctime">>). %% ctime is not a valid pax header
247-define(PAX_GID, <<"gid">>).
248-define(PAX_GNAME, <<"gname">>).
249-define(PAX_LINKPATH, <<"linkpath">>).
250-define(PAX_MTIME, <<"mtime">>).
251-define(PAX_PATH, <<"path">>).
252-define(PAX_SIZE, <<"size">>).
253-define(PAX_UID, <<"uid">>).
254-define(PAX_UNAME, <<"uname">>).
255-define(PAX_XATTR, <<"SCHILY.xattr.">>).
256-define(PAX_XATTR_STR, "SCHILY.xattr.").
257-define(PAX_NONE, <<"">>).
258
259%% Tar format constants
260%% Unknown format
261-define(FORMAT_UNKNOWN, 0).
262%% The format of the original Unix V7 tar tool prior to standardization
263-define(FORMAT_V7, 1).
264%% The old and new GNU formats, incompatible with USTAR.
265%% This covers the old GNU sparse extension, but it does
266%% not cover the GNU sparse extensions using PAX headers,
267%% versions 0.0, 0.1, and 1.0; these fall under the PAX format.
268-define(FORMAT_GNU, 2).
269%% Schily's tar format, which is incompatible with USTAR.
270%% This does not cover STAR extensions to the PAX format; these
271%% fall under the PAX format.
272-define(FORMAT_STAR, 3).
273%% USTAR is the former standardization of tar defined in POSIX.1-1988,
274%% it is incompatible with the GNU and STAR formats.
275-define(FORMAT_USTAR, 4).
276%% PAX is the latest standardization of tar defined in POSIX.1-2001.
277%% This is an extension of USTAR and is "backwards compatible" with it.
278%%
279%% Some newer formats add their own extensions to PAX, such as GNU sparse
280%% files and SCHILY extended attributes. Since they are backwards compatible
281%% with PAX, they will be labelled as "PAX".
282-define(FORMAT_PAX, 5).
283
284%% Magic constants
285-define(MAGIC_GNU, <<"ustar ">>).
286-define(VERSION_GNU, <<" \x00">>).
287-define(MAGIC_USTAR, <<"ustar\x00">>).
288-define(VERSION_USTAR, <<"00">>).
289-define(TRAILER_STAR, <<"tar\x00">>).
290
291%% Size constants
292-define(BLOCK_SIZE, 512). %% size of each block in a tar stream
293-define(NAME_SIZE, 100). %% max length of the name field in USTAR format
294-define(PREFIX_SIZE, 155). %% max length of the prefix field in USTAR format
295
296%% Maximum size of a nanosecond value as an integer
297-define(MAX_NANO_INT_SIZE, 9).
298%% Maximum size of a 64-bit signed integer
299-define(MAX_INT64, (1 bsl 63 - 1)).
300
301-define(PAX_GNU_SPARSE_NUMBLOCKS, <<"GNU.sparse.numblocks">>).
302-define(PAX_GNU_SPARSE_OFFSET, <<"GNU.sparse.offset">>).
303-define(PAX_GNU_SPARSE_NUMBYTES, <<"GNU.sparse.numbytes">>).
304-define(PAX_GNU_SPARSE_MAP, <<"GNU.sparse.map">>).
305-define(PAX_GNU_SPARSE_NAME, <<"GNU.sparse.name">>).
306-define(PAX_GNU_SPARSE_MAJOR, <<"GNU.sparse.major">>).
307-define(PAX_GNU_SPARSE_MINOR, <<"GNU.sparse.minor">>).
308-define(PAX_GNU_SPARSE_SIZE, <<"GNU.sparse.size">>).
309-define(PAX_GNU_SPARSE_REALSIZE, <<"GNU.sparse.realsize">>).
310
311-define(V7_NAME, 0).
312-define(V7_NAME_LEN, 100).
313-define(V7_MODE, 100).
314-define(V7_MODE_LEN, 8).
315-define(V7_UID, 108).
316-define(V7_UID_LEN, 8).
317-define(V7_GID, 116).
318-define(V7_GID_LEN, 8).
319-define(V7_SIZE, 124).
320-define(V7_SIZE_LEN, 12).
321-define(V7_MTIME, 136).
322-define(V7_MTIME_LEN, 12).
323-define(V7_CHKSUM, 148).
324-define(V7_CHKSUM_LEN, 8).
325-define(V7_TYPE, 156).
326-define(V7_TYPE_LEN, 1).
327-define(V7_LINKNAME, 157).
328-define(V7_LINKNAME_LEN, 100).
329
330-define(STAR_TRAILER, 508).
331-define(STAR_TRAILER_LEN, 4).
332
333-define(USTAR_MAGIC, 257).
334-define(USTAR_MAGIC_LEN, 6).
335-define(USTAR_VERSION, 263).
336-define(USTAR_VERSION_LEN, 2).
337-define(USTAR_UNAME, 265).
338-define(USTAR_UNAME_LEN, 32).
339-define(USTAR_GNAME, 297).
340-define(USTAR_GNAME_LEN, 32).
341-define(USTAR_DEVMAJ, 329).
342-define(USTAR_DEVMAJ_LEN, 8).
343-define(USTAR_DEVMIN, 337).
344-define(USTAR_DEVMIN_LEN, 8).
345-define(USTAR_PREFIX, 345).
346-define(USTAR_PREFIX_LEN, 155).
347
348-define(GNU_MAGIC, 257).
349-define(GNU_MAGIC_LEN, 6).
350-define(GNU_VERSION, 263).
351-define(GNU_VERSION_LEN, 2).
352
353%% ?BLOCK_SIZE of zero-bytes.
354%% Two of these in a row mark the end of an archive.
355-define(ZERO_BLOCK, <<0,0,0,0,0,0,0,0,0,0,
356                      0,0,0,0,0,0,0,0,0,0,
357                      0,0,0,0,0,0,0,0,0,0,
358                      0,0,0,0,0,0,0,0,0,0,
359                      0,0,0,0,0,0,0,0,0,0,
360                      0,0,0,0,0,0,0,0,0,0,
361                      0,0,0,0,0,0,0,0,0,0,
362                      0,0,0,0,0,0,0,0,0,0,
363                      0,0,0,0,0,0,0,0,0,0,
364                      0,0,0,0,0,0,0,0,0,0,
365                      0,0,0,0,0,0,0,0,0,0,
366                      0,0,0,0,0,0,0,0,0,0,
367                      0,0,0,0,0,0,0,0,0,0,
368                      0,0,0,0,0,0,0,0,0,0,
369                      0,0,0,0,0,0,0,0,0,0,
370                      0,0,0,0,0,0,0,0,0,0,
371                      0,0,0,0,0,0,0,0,0,0,
372                      0,0,0,0,0,0,0,0,0,0,
373                      0,0,0,0,0,0,0,0,0,0,
374                      0,0,0,0,0,0,0,0,0,0,
375                      0,0,0,0,0,0,0,0,0,0,
376                      0,0,0,0,0,0,0,0,0,0,
377                      0,0,0,0,0,0,0,0,0,0,
378                      0,0,0,0,0,0,0,0,0,0,
379                      0,0,0,0,0,0,0,0,0,0,
380                      0,0,0,0,0,0,0,0,0,0,
381                      0,0,0,0,0,0,0,0,0,0,
382                      0,0,0,0,0,0,0,0,0,0,
383                      0,0,0,0,0,0,0,0,0,0,
384                      0,0,0,0,0,0,0,0,0,0,
385                      0,0,0,0,0,0,0,0,0,0,
386                      0,0,0,0,0,0,0,0,0,0,
387                      0,0,0,0,0,0,0,0,0,0,
388                      0,0,0,0,0,0,0,0,0,0,
389                      0,0,0,0,0,0,0,0,0,0,
390                      0,0,0,0,0,0,0,0,0,0,
391                      0,0,0,0,0,0,0,0,0,0,
392                      0,0,0,0,0,0,0,0,0,0,
393                      0,0,0,0,0,0,0,0,0,0,
394                      0,0,0,0,0,0,0,0,0,0,
395                      0,0,0,0,0,0,0,0,0,0,
396                      0,0,0,0,0,0,0,0,0,0,
397                      0,0,0,0,0,0,0,0,0,0,
398                      0,0,0,0,0,0,0,0,0,0,
399                      0,0,0,0,0,0,0,0,0,0,
400                      0,0,0,0,0,0,0,0,0,0,
401                      0,0,0,0,0,0,0,0,0,0,
402                      0,0,0,0,0,0,0,0,0,0,
403                      0,0,0,0,0,0,0,0,0,0,
404                      0,0,0,0,0,0,0,0,0,0,
405                      0,0,0,0,0,0,0,0,0,0,0,0>>).
406
407-define(BILLION, 1000000000).
408
409-define(EPOCH, {{1970,1,1}, {0,0,0}}).
410