POSIX extended format headers do not include PID by default

The intent is to make binary-equivalent PAX archives easy to create.  If
POSIXLY_CORRECT is set, the POSIX standard default is used, which embeds
the pid.

* src/common.h (posixly_correct): New global.
* src/tar.c (decode_options): Detect the POSIXLY_CORRECT environment
variable.
* src/buffer.c (add_chunk_header): Change filenames of multipart files to
omit the pid.
* src/xheader.c (HEADER_TEMPLATE): New macro.
(xheader_xhdr_name, xheader_ghdr_name): Use HEADER_TEMPLATE to select
the template for the POSIX extended header name.
* doc/tar.texi: Document the change.

Signed-off-by: Zachary Vance <za3k@za3k.com>

diff --git a/doc/tar.texi b/doc/tar.texi
index 71318f3e0fc67feb1a0ac24bde6640f2f89c685b..0296c4299bae849fe6ad21fdf516b0c454735220 100644 (file)
--- a/doc/tar.texi
+++ b/doc/tar.texi
@@ -10458,9 +10458,16 @@ If no option @samp{exthdr.name=string} is specified, @command{tar}
 will use the following default value:
 
 @smallexample
-%d/PaxHeaders.%p/%f
+%d/PaxHeaders/%f
 @end smallexample
 
+This default is selected to ensure the reproducibility of the
+archive. @acronym{POSIX} standard recommends to use
+@samp{%d/PaxHeaders.%p/%f} instead, which means the two archives
+created with the same set of options and containing the same set
+of files will be byte-to-byte different. This default will be used
+if the environment variable @env{POSIXLY_CORRECT} is set.
+
 @item exthdr.mtime=@var{value}
 
 This keyword defines the value of the @samp{mtime} field that
@@ -10489,12 +10496,18 @@ Any other @samp{%} characters in @var{string} produce undefined results.
 If no option @samp{globexthdr.name=string} is specified, @command{tar}
 will use the following default value:
 
+@smallexample
+$TMPDIR/GlobalHead.%n
+@end smallexample
+
+If the environment variable @env{POSIXLY_CORRECT} is set, the
+following value is used instead:
+
 @smallexample
 $TMPDIR/GlobalHead.%p.%n
 @end smallexample
 
-@noindent
-where @samp{$TMPDIR} represents the value of the @var{TMPDIR}
+In both cases, @samp{$TMPDIR} stands for the value of the @var{TMPDIR}
 environment variable.  If @var{TMPDIR} is not set, @command{tar}
 uses @samp{/tmp}.
 
@@ -10557,7 +10570,7 @@ archives created using it, will be binary equivalent if they have the
 same contents:
 
 @smallexample
---pax-option=exthdr.name=%d/PaxHeaders/%f,atime:=0
+--pax-option=atime:=0
 @end smallexample
 
 @noindent
@@ -10566,14 +10579,27 @@ from them, you will also need to eliminate changes due to ctime, as
 shown in examples below:
 
 @smallexample
---pax-option=exthdr.name=%d/PaxHeaders/%f,atime:=0,ctime:=0
+--pax-option=atime:=0,ctime:=0
 @end smallexample
 
 @noindent
 or
 
 @smallexample
---pax-option=exthdr.name=%d/PaxHeaders/%f,atime:=0,delete=ctime
+--pax-option=atime:=0,delete=ctime
+@end smallexample
+
+Notice, that if you create an archive in POSIX format (@pxref{posix})
+and the environment variable @env{POSIXLY_CORRECT} is set, then the
+two archives created using the same options on the same set of files
+will not be byte-to-byte equivalent even with the above option.  This
+is because the posix default for extended header names includes the
+PID of the tar process, which is different at each run. To produce
+byte-to-byte equivalent archives in this case, either unset
+@env{POSIXLY_CORRECT}, or use the following option:
+
+@smallexample
+---pax-option=exthdr.name=%d/PaxHeaders/%f,atime:=0,ctime:=0
 @end smallexample
 
 @node Checksumming
@@ -10699,7 +10725,7 @@ GNU extensions.  More specifically, the very first part retains its
 original name, and all subsequent parts are named using the pattern:
 
 @smallexample
-%d/GNUFileParts.%p/%f.%n
+%d/GNUFileParts/%f.%n
 @end smallexample
 
 @noindent
@@ -10718,13 +10744,12 @@ created the archive.
 @end multitable
 
 For example, if the file @file{var/longfile} was split during archive
-creation between three volumes, and the creator @command{tar} process
-had process @acronym{ID} @samp{27962}, then the member names will be:
+creation between three volumes, then the member names will be:
 
 @smallexample
 var/longfile
-var/GNUFileParts.27962/longfile.1
-var/GNUFileParts.27962/longfile.2
+var/GNUFileParts/longfile.1
+var/GNUFileParts/longfile.2
 @end smallexample
 
 When you extract your archive using a third-party @command{tar}, these
@@ -10735,9 +10760,9 @@ the proper order, for example:
 @smallexample
 @group
 $ @kbd{cd var}
-$ @kbd{cat GNUFileParts.27962/longfile.1 \
-  GNUFileParts.27962/longfile.2 >> longfile}
-$ rm -f GNUFileParts.27962
+$ @kbd{cat GNUFileParts/longfile.1 \
+  GNUFileParts/longfile.2 >> longfile}
+$ rm -f GNUFileParts
 @end group
 @end smallexample
 
@@ -10763,12 +10788,12 @@ more warnings and more files generated on your disk, e.g.:
 @smallexample
 @group
 $ @kbd{tar xf vol-1.tar}
-var/PaxHeaders.27962/longfile: Unknown file type 'x', extracted as
+var/PaxHeaders/longfile: Unknown file type 'x', extracted as
 normal file
 Unexpected EOF in archive
 $ @kbd{tar xf vol-2.tar}
-tmp/GlobalHead.27962.1: Unknown file type 'g', extracted as normal file
-GNUFileParts.27962/PaxHeaders.27962/sparsefile.1: Unknown file type
+tmp/GlobalHead.1: Unknown file type 'g', extracted as normal file
+GNUFileParts/PaxHeaders/sparsefile.1: Unknown file type
 'x', extracted as normal file
 @end group
 @end smallexample
@@ -10884,8 +10909,8 @@ use.  Continuing our example:
 
 @smallexample
 @group
-$ @kbd{xsparse -v -x /home/gray/PaxHeaders.6058/sparsefile \
-  /home/gray/GNUSparseFile.6058/sparsefile}
+$ @kbd{xsparse -v -x /home/gray/PaxHeaders/sparsefile \
+  /home/gray/GNUSparseFile/sparsefile}
 Reading extended header file
 Found variable GNU.sparse.major = 1
 Found variable GNU.sparse.minor = 0
@@ -10915,8 +10940,7 @@ If you use a @command{tar} implementation that does not support PAX
 format, extended headers for each member will be extracted as a
 separate file.  If we represent the member name as
 @file{@var{dir}/@var{name}}, then the extended header file will be
-named @file{@var{dir}/@/PaxHeaders.@var{n}/@/@var{name}}, where
-@var{n} is an integer number.
+named @file{@var{dir}/@/PaxHeaders/@/@var{name}}.
 
 Things become more difficult if your @command{tar} implementation
 does support PAX headers, because in this case you will have to

diff --git a/src/buffer.c b/src/buffer.c
index 7781009a04407e97dac75b76eb32a0e2a09ed9e7..151710cec53a7a53fa037201e8ef000e864f431c 100644 (file)
--- a/src/buffer.c
+++ b/src/buffer.c
@@ -1731,7 +1731,7 @@ add_chunk_header (struct bufmap *map)
       st.stat.st_uid = getuid ();
       st.stat.st_gid = getgid ();
       st.orig_file_name = xheader_format_name (&st,
-                                               "%d/GNUFileParts.%p/%f.%n",
+                                               "%d/GNUFileParts/%f.%n",
                                                volno);
       st.file_name = st.orig_file_name;
       st.archive_file_size = st.stat.st_size = map->sizeleft;

diff --git a/src/common.h b/src/common.h
index 501e0d3a777b82f92a19b9652df5a75c595c379a..2396e767b44922b9402cd9460e627155e0f0b1fe 100644 (file)
--- a/src/common.h
+++ b/src/common.h
@@ -340,6 +340,9 @@ GLOBAL const char *volume_label_option;
 \f
 /* Other global variables.  */
 
+/* Force POSIX-compliance */
+GLOBAL bool posixly_correct;
+
 /* File descriptor for archive file.  */
 GLOBAL int archive;
 

diff --git a/src/tar.c b/src/tar.c
index d66fed8696fc41e8682792b1ede3872c7b21dcfe..250f9f2d252e2c62dad7411794a847472c219364 100644 (file)
--- a/src/tar.c
+++ b/src/tar.c
@@ -2230,6 +2230,8 @@ decode_options (int argc, char **argv)
   args.version_control_string = 0;
   args.compress_autodetect = false;
 
+  posixly_correct = getenv ("POSIXLY_CORRECT") != NULL;
+
   subcommand_option = UNKNOWN_SUBCOMMAND;
   archive_format = DEFAULT_FORMAT;
   blocking_factor = DEFAULT_BLOCKING;

diff --git a/src/xheader.c b/src/xheader.c
index 46bf4bbe0c6a019397c33497088ad3503273a92f..eaeea5d4917b04c254ec1c3827b41c5d989708a1 100644 (file)
--- a/src/xheader.c
+++ b/src/xheader.c
@@ -369,29 +369,46 @@ xheader_format_name (struct tar_stat_info *st, const char *fmt, size_t n)
   return buf;
 }
 
+/* Table of templates for the names of POSIX extended headers.
+   Indexed by the the type of the header (per-file or global)
+   and POSIX compliance mode (0 or q depending on whether
+   POSIXLY_CORRECT environment variable is set. */
+static const char *header_template[][2] = {
+  /* Individual header templates: */
+  { "%d/PaxHeaders/%f", "%d/PaxHeaders.%p/%f" },
+  /* Global header templates: */
+  { "/GlobalHead.%n", "/GlobalHead.%p.%n" }
+};
+/* Indices to the above table */
+enum {
+  pax_file_header,
+  pax_global_header
+};
+/* Return the name for the POSIX extended header T */
+#define HEADER_TEMPLATE(t) header_template[t][posixly_correct]
+
 char *
 xheader_xhdr_name (struct tar_stat_info *st)
 {
   if (!exthdr_name)
-    assign_string (&exthdr_name, "%d/PaxHeaders.%p/%f");
+    assign_string (&exthdr_name, HEADER_TEMPLATE (pax_file_header));
   return xheader_format_name (st, exthdr_name, 0);
 }
 
-#define GLOBAL_HEADER_TEMPLATE "/GlobalHead.%p.%n"
-
 char *
 xheader_ghdr_name (void)
 {
   if (!globexthdr_name)
     {
       size_t len;
+      const char *global_header_template = HEADER_TEMPLATE (pax_global_header);
       const char *tmp = getenv ("TMPDIR");
       if (!tmp)
        tmp = "/tmp";
-      len = strlen (tmp) + sizeof (GLOBAL_HEADER_TEMPLATE); /* Includes nul */
+      len = strlen (tmp) + strlen (global_header_template) + 1;
       globexthdr_name = xmalloc (len);
       strcpy(globexthdr_name, tmp);
-      strcat(globexthdr_name, GLOBAL_HEADER_TEMPLATE);
+      strcat(globexthdr_name, global_header_template);
     }
 
   return xheader_format_name (NULL, globexthdr_name, global_header_count + 1);