From: Pedro Alvarez Piedehierro <palvare...@gmail.com> Importing gcc tarballs[1] with import-tars script (in contrib) fails when hitting a pax extended header.
Make sure we always read the extended attributes from the pax entries, and store the 'path' value if found to be used in the next ustar entry. The code to parse pax extended headers was written consulting the Pax Pax Interchange Format documentation [2]. [1] http://ftp.gnu.org/gnu/gcc/gcc-7.3.0/gcc-7.3.0.tar.xz [2] https://www.freebsd.org/cgi/man.cgi?manpath=FreeBSD+8-current&query=tar&sektion=5 Signed-off-by: Pedro Alvarez <palvare...@gmail.com> --- contrib/fast-import/import-tars.perl | 31 +++++++++++++++++++++++++++++-- 1 file changed, 29 insertions(+), 2 deletions(-) diff --git a/contrib/fast-import/import-tars.perl b/contrib/fast-import/import-tars.perl index d60b4315ed..e800d9f5c9 100755 --- a/contrib/fast-import/import-tars.perl +++ b/contrib/fast-import/import-tars.perl @@ -63,6 +63,8 @@ foreach my $tar_file (@ARGV) my $have_top_dir = 1; my ($top_dir, %files); + my $next_path = ''; + while (read(I, $_, 512) == 512) { my ($name, $mode, $uid, $gid, $size, $mtime, $chksum, $typeflag, $linkname, $magic, @@ -70,6 +72,13 @@ foreach my $tar_file (@ARGV) $prefix) = unpack 'Z100 Z8 Z8 Z8 Z12 Z12 Z8 Z1 Z100 Z6 Z2 Z32 Z32 Z8 Z8 Z*', $_; + + unless ($next_path eq '') { + # Recover name from previous extended header + $name = $next_path; + $next_path = ''; + } + last unless length($name); if ($name eq '././@LongLink') { # GNU tar extension @@ -90,13 +99,31 @@ foreach my $tar_file (@ARGV) Z8 Z1 Z100 Z6 Z2 Z32 Z32 Z8 Z8 Z*', $_; } - next if $name =~ m{/\z}; $mode = oct $mode; $size = oct $size; $mtime = oct $mtime; next if $typeflag == 5; # directory - if ($typeflag != 1) { # handle hard links later + if ($typeflag eq 'x') { # extended header + # If extended header, check for path + my $pax_header = ''; + while ($size > 0 && read(I, $_, 512) == 512) { + $pax_header = $pax_header . substr($_, 0, $size); + $size -= 512; + } + + my @lines = split /\n/, $pax_header; + foreach my $line (@lines) { + my ($len, $entry) = split / /, $line; + my ($key, $value) = split /=/, $entry; + if ($key eq 'path') { + $next_path = $value; + } + } + next; + } elsif ($name =~ m{/\z}) { # directory + next; + } elsif ($typeflag != 1) { # handle hard links later print FI "blob\n", "mark :$next_mark\n"; if ($typeflag == 2) { # symbolic link print FI "data ", length($linkname), "\n", -- 2.11.0
