#!/usr/bin/perl -w
-# Known limitations:
-# - does not propagate permissions
-# - tells "ready for commit" even when things could not be completed
-# (not sure this is true anymore, more testing is needed)
-# - does not handle whitespace in pathnames at all.
-
use strict;
use Getopt::Std;
use File::Temp qw(tempdir);
use Data::Dumper;
use File::Basename qw(basename dirname);
+use File::Spec;
+use Git;
-unless ($ENV{GIT_DIR} && -r $ENV{GIT_DIR}){
- die "GIT_DIR is not defined or is unreadable";
-}
-
-our ($opt_h, $opt_p, $opt_v, $opt_c, $opt_f, $opt_a, $opt_m );
+our ($opt_h, $opt_P, $opt_p, $opt_v, $opt_c, $opt_f, $opt_a, $opt_m, $opt_d, $opt_u, $opt_w, $opt_W, $opt_k);
-getopts('hpvcfam:');
+getopts('uhPpvcfkam:d:w:W');
$opt_h && usage();
die "Need at least one commit identifier!" unless @ARGV;
-# setup a tempdir
-our ($tmpdir, $tmpdirname) = tempdir('git-cvsapplycommit-XXXXXX',
- TMPDIR => 1,
- CLEANUP => 1);
+# Get git-config settings
+my $repo = Git->repository();
+$opt_w = $repo->config('cvsexportcommit.cvsdir') unless defined $opt_w;
+
+if ($opt_w || $opt_W) {
+ # Remember where GIT_DIR is before changing to CVS checkout
+ unless ($ENV{GIT_DIR}) {
+ # No GIT_DIR set. Figure it out for ourselves
+ my $gd =`git-rev-parse --git-dir`;
+ chomp($gd);
+ $ENV{GIT_DIR} = $gd;
+ }
+ # Make sure GIT_DIR is absolute
+ $ENV{GIT_DIR} = File::Spec->rel2abs($ENV{GIT_DIR});
+}
+
+if ($opt_w) {
+ if (! -d $opt_w."/CVS" ) {
+ die "$opt_w is not a CVS checkout";
+ }
+ chdir $opt_w or die "Cannot change to CVS checkout at $opt_w";
+}
+unless ($ENV{GIT_DIR} && -r $ENV{GIT_DIR}){
+ die "GIT_DIR is not defined or is unreadable";
+}
+
+
+my @cvs;
+if ($opt_d) {
+ @cvs = ('cvs', '-d', $opt_d);
+} else {
+ @cvs = ('cvs');
+}
# resolve target commit
my $commit;
}
}
+my $noparent = "0000000000000000000000000000000000000000";
if ($parent) {
my $found;
# double check that it's a valid parent
last;
}; # found it
}
- die "Did not find $parent in the parents for this commit!" if !$found;
+ die "Did not find $parent in the parents for this commit!" if !$found and !$opt_P;
} else { # we don't have a parent from the cmdline...
if (@parents == 1) { # it's safe to get it from the commit
$parent = $parents[0];
- } else { # or perhaps not!
- die "This commit has more than one parent -- please name the parent you want to use explicitly";
+ } elsif (@parents == 0) { # there is no parent
+ $parent = $noparent;
+ } else { # cannot choose automatically from multiple parents
+ die "This commit has more than one parent -- please name the parent you want to use explicitly";
}
}
+my $go_back_to = 0;
+
+if ($opt_W) {
+ $opt_v && print "Resetting to $parent\n";
+ $go_back_to = `git symbolic-ref HEAD 2> /dev/null ||
+ git rev-parse HEAD` || die "Could not determine current branch";
+ system("git checkout -q $parent^0") && die "Could not check out $parent^0";
+}
+
$opt_v && print "Applying to CVS commit $commit from parent $parent\n";
# grab the commit message
}
close MSG;
-my (@afiles, @dfiles, @mfiles, @dirs);
-my %amodes;
-my @files = safe_pipe_capture('git-diff-tree', '-r', $parent, $commit);
-#print @files;
-$? && die "Error in git-diff-tree";
-foreach my $f (@files) {
- chomp $f;
- my @fields = split(m!\s+!, $f);
- if ($fields[4] eq 'A') {
- my $path = $fields[5];
- $amodes{$path} = $fields[1];
- push @afiles, $path;
- # add any needed parent directories
- $path = dirname $path;
- while (!-d $path and ! grep { $_ eq $path } @dirs) {
- unshift @dirs, $path;
- $path = dirname $path;
- }
- }
- if ($fields[4] eq 'M') {
- push @mfiles, $fields[5];
- }
- if ($fields[4] eq 'D') {
- push @dfiles, $fields[5];
- }
+if ($parent eq $noparent) {
+ `git-diff-tree --binary -p --root $commit >.cvsexportcommit.diff`;# || die "Cannot diff";
+} else {
+ `git-diff-tree --binary -p $parent $commit >.cvsexportcommit.diff`;# || die "Cannot diff";
+}
+
+## apply non-binary changes
+
+# In pedantic mode require all lines of context to match. In normal
+# mode, be compatible with diff/patch: assume 3 lines of context and
+# require at least one line match, i.e. ignore at most 2 lines of
+# context, like diff/patch do by default.
+my $context = $opt_p ? '' : '-C1';
+
+print "Checking if patch will apply\n";
+
+my @stat;
+open APPLY, "GIT_DIR= git-apply $context --summary --numstat<.cvsexportcommit.diff|" || die "cannot patch";
+@stat=<APPLY>;
+close APPLY || die "Cannot patch";
+my (@bfiles,@files,@afiles,@dfiles);
+chomp @stat;
+foreach (@stat) {
+ push (@bfiles,$1) if m/^-\t-\t(.*)$/;
+ push (@files, $1) if m/^-\t-\t(.*)$/;
+ push (@files, $1) if m/^\d+\t\d+\t(.*)$/;
+ push (@afiles,$1) if m/^ create mode [0-7]+ (.*)$/;
+ push (@dfiles,$1) if m/^ delete mode [0-7]+ (.*)$/;
}
-my (@binfiles, @abfiles, @dbfiles, @bfiles, @mbfiles);
-@binfiles = grep m/^Binary files/, safe_pipe_capture('git-diff-tree', '-p', $parent, $commit);
-map { chomp } @binfiles;
-@abfiles = grep s/^Binary files \/dev\/null and b\/(.*) differ$/$1/, @binfiles;
-@dbfiles = grep s/^Binary files a\/(.*) and \/dev\/null differ$/$1/, @binfiles;
-@mbfiles = grep s/^Binary files a\/(.*) and b\/(.*) differ$/$1/, @binfiles;
-push @bfiles, @abfiles;
-push @bfiles, @dbfiles;
-push @bfiles, @mbfiles;
-push @mfiles, @mbfiles;
-
-$opt_v && print "The commit affects:\n ";
-$opt_v && print join ("\n ", @afiles,@mfiles,@dfiles) . "\n\n";
-undef @files; # don't need it anymore
+map { s/^"(.*)"$/$1/g } @bfiles,@files;
+map { s/\\([0-7]{3})/sprintf('%c',oct $1)/eg } @bfiles,@files;
# check that the files are clean and up to date according to cvs
my $dirty;
+my @dirs;
+foreach my $p (@afiles) {
+ my $path = dirname $p;
+ while (!-d $path and ! grep { $_ eq $path } @dirs) {
+ unshift @dirs, $path;
+ $path = dirname $path;
+ }
+}
+
+# ... check dirs,
foreach my $d (@dirs) {
if (-e $d) {
$dirty = 1;
warn "$d exists and is not a directory!\n";
}
}
-foreach my $f (@afiles) {
- # This should return only one value
- if ($f =~ m,(.*)/[^/]*$,) {
- my $p = $1;
- next if (grep { $_ eq $p } @dirs);
+
+# ... query status of all files that we have a directory for and parse output of 'cvs status' to %cvsstat.
+my @canstatusfiles;
+foreach my $f (@files) {
+ my $path = dirname $f;
+ next if (grep { $_ eq $path } @dirs);
+ push @canstatusfiles, $f;
+}
+
+my %cvsstat;
+if (@canstatusfiles) {
+ if ($opt_u) {
+ my @updated = xargs_safe_pipe_capture([@cvs, 'update'], @canstatusfiles);
+ print @updated;
}
- my @status = grep(m/^File/, safe_pipe_capture('cvs', '-q', 'status' ,$f));
- if (@status > 1) { warn 'Strange! cvs status returned more than one line?'};
- if (-d dirname $f and $status[0] !~ m/Status: Unknown$/
- and $status[0] !~ m/^File: no file /) {
- $dirty = 1;
- warn "File $f is already known in your CVS checkout -- perhaps it has been added by another user. Or this may indicate that it exists on a different branch. If this is the case, use -f to force the merge.\n";
- warn "Status was: $status[0]\n";
+ # "cvs status" reorders the parameters, notably when there are multiple
+ # arguments with the same basename. So be precise here.
+
+ my %added = map { $_ => 1 } @afiles;
+ my %todo = map { $_ => 1 } @canstatusfiles;
+
+ while (%todo) {
+ my @canstatusfiles2 = ();
+ my %fullname = ();
+ foreach my $name (keys %todo) {
+ my $basename = basename($name);
+
+ # CVS reports files that don't exist in the current revision as
+ # "no file $basename" in its "status" output, so we should
+ # anticipate that. Totally unknown files will have a status
+ # "Unknown". However, if they exist in the Attic, their status
+ # will be "Up-to-date" (this means they were added once but have
+ # been removed).
+ $basename = "no file $basename" if $added{$basename};
+
+ $basename =~ s/^\s+//;
+ $basename =~ s/\s+$//;
+
+ if (!exists($fullname{$basename})) {
+ $fullname{$basename} = $name;
+ push (@canstatusfiles2, $name);
+ delete($todo{$name});
+ }
+ }
+ my @cvsoutput;
+ @cvsoutput = xargs_safe_pipe_capture([@cvs, 'status'], @canstatusfiles2);
+ foreach my $l (@cvsoutput) {
+ chomp $l;
+ next unless
+ my ($file, $status) = $l =~ /^File:\s+(.*\S)\s+Status: (.*)$/;
+
+ my $fullname = $fullname{$file};
+ print STDERR "Huh? Status '$status' reported for unexpected file '$file'\n"
+ unless defined $fullname;
+
+ # This response means the file does not exist except in
+ # CVS's attic, so set the status accordingly
+ $status = "In-attic"
+ if $file =~ /^no file /
+ && $status eq 'Up-to-date';
+
+ $cvsstat{$fullname{$file}} = $status
+ if defined $fullname{$file};
+ }
}
}
-foreach my $f (@mfiles, @dfiles) {
+# ... Validate that new files have the correct status
+foreach my $f (@afiles) {
+ next unless defined(my $stat = $cvsstat{$f});
+
+ # This means the file has never been seen before
+ next if $stat eq 'Unknown';
+
+ # This means the file has been seen before but was removed
+ next if $stat eq 'In-attic';
+
+ $dirty = 1;
+ warn "File $f is already known in your CVS checkout -- perhaps it has been added by another user. Or this may indicate that it exists on a different branch. If this is the case, use -f to force the merge.\n";
+ warn "Status was: $cvsstat{$f}\n";
+}
+
+# ... validate known files.
+foreach my $f (@files) {
+ next if grep { $_ eq $f } @afiles;
# TODO:we need to handle removed in cvs
- my @status = grep(m/^File/, safe_pipe_capture('cvs', '-q', 'status' ,$f));
- if (@status > 1) { warn 'Strange! cvs status returned more than one line?'};
- unless ($status[0] =~ m/Status: Up-to-date$/) {
+ unless (defined ($cvsstat{$f}) and $cvsstat{$f} eq "Up-to-date") {
$dirty = 1;
- warn "File $f not up to date in your CVS checkout!\n";
+ warn "File $f not up to date but has status '$cvsstat{$f}' in your CVS checkout!\n";
+ }
+
+ # Depending on how your GIT tree got imported from CVS you may
+ # have a conflict between expanded keywords in your CVS tree and
+ # unexpanded keywords in the patch about to be applied.
+ if ($opt_k) {
+ my $orig_file ="$f.orig";
+ rename $f, $orig_file;
+ open(FILTER_IN, "<$orig_file") or die "Cannot open $orig_file\n";
+ open(FILTER_OUT, ">$f") or die "Cannot open $f\n";
+ while (<FILTER_IN>)
+ {
+ my $line = $_;
+ $line =~ s/\$([A-Z][a-z]+):[^\$]+\$/\$$1\$/g;
+ print FILTER_OUT $line;
+ }
+ close FILTER_IN;
+ close FILTER_OUT;
}
}
+
if ($dirty) {
if ($opt_f) { warn "The tree is not clean -- forced merge\n";
$dirty = 0;
}
}
-###
-### NOTE: if you are planning to die() past this point
-### you MUST call cleanupcvs(@files) before die()
-###
+print "Applying\n";
+if ($opt_W) {
+ system("git checkout -q $commit^0") && die "cannot patch";
+} else {
+ `GIT_DIR= git-apply $context --summary --numstat --apply <.cvsexportcommit.diff` || die "cannot patch";
+}
+
+print "Patch applied successfully. Adding new files and directories to CVS\n";
+my $dirtypatch = 0;
+#
+# We have to add the directories in order otherwise we will have
+# problems when we try and add the sub-directory of a directory we
+# have not added yet.
+#
+# Luckily this is easy to deal with by sorting the directories and
+# dealing with the shortest ones first.
+#
+@dirs = sort { length $a <=> length $b} @dirs;
-print "Creating new directories\n";
foreach my $d (@dirs) {
- unless (mkdir $d) {
- warn "Could not mkdir $d: $!";
- $dirty = 1;
- }
- `cvs add $d`;
- if ($?) {
- $dirty = 1;
+ if (system(@cvs,'add',$d)) {
+ $dirtypatch = 1;
warn "Failed to cvs add directory $d -- you may need to do it manually";
}
}
-print "'Patching' binary files\n";
-
-foreach my $f (@bfiles) {
- # check that the file in cvs matches the "old" file
- # extract the file to $tmpdir and compare with cmp
- if (not(grep { $_ eq $f } @afiles)) {
- my $tree = safe_pipe_capture('git-rev-parse', "$parent^{tree}");
- chomp $tree;
- my $blob = `git-ls-tree $tree "$f" | cut -f 1 | cut -d ' ' -f 3`;
- chomp $blob;
- `git-cat-file blob $blob > $tmpdir/blob`;
- if (system('cmp', '-s', $f, "$tmpdir/blob")) {
- warn "Binary file $f in CVS does not match parent.\n";
- if (not $opt_f) {
- $dirty = 1;
- next;
- }
- }
- }
- if (not(grep { $_ eq $f } @dfiles)) {
- my $tree = safe_pipe_capture('git-rev-parse', "$commit^{tree}");
- chomp $tree;
- my $blob = `git-ls-tree $tree "$f" | cut -f 1 | cut -d ' ' -f 3`;
- chomp $blob;
- # replace with the new file
- `git-cat-file blob $blob > $f`;
- }
-
- # TODO: something smart with file modes
-
-}
-if ($dirty) {
- cleanupcvs(@files);
- die "Exiting: Binary files in CVS do not match parent";
-}
-
-## apply non-binary changes
-my $fuzz = $opt_p ? 0 : 2;
-
-print "Patching non-binary files\n";
-
-if (scalar(@afiles)+scalar(@dfiles)+scalar(@mfiles) != scalar(@bfiles)) {
- print `(git-diff-tree -p $parent -p $commit | patch -p1 -F $fuzz ) 2>&1`;
-}
-
-my $dirtypatch = 0;
-if (($? >> 8) == 2) {
- cleanupcvs(@files);
- die "Exiting: Patch reported serious trouble -- you will have to apply this patch manually";
-} elsif (($? >> 8) == 1) { # some hunks failed to apply
- $dirtypatch = 1;
-}
-
foreach my $f (@afiles) {
- set_new_file_permissions($f, $amodes{$f});
if (grep { $_ eq $f } @bfiles) {
- system('cvs', 'add','-kb',$f);
+ system(@cvs, 'add','-kb',$f);
} else {
- system('cvs', 'add', $f);
+ system(@cvs, 'add', $f);
}
if ($?) {
- $dirty = 1;
+ $dirtypatch = 1;
warn "Failed to cvs add $f -- you may need to do it manually";
}
}
foreach my $f (@dfiles) {
- system('cvs', 'rm', '-f', $f);
+ system(@cvs, 'rm', '-f', $f);
if ($?) {
- $dirty = 1;
+ $dirtypatch = 1;
warn "Failed to cvs rm -f $f -- you may need to do it manually";
}
}
print "Commit to CVS\n";
-print "Patch: $title\n";
-my $commitfiles = join(' ', @afiles, @mfiles, @dfiles);
-my $cmd = "cvs commit -F .msg $commitfiles";
+print "Patch title (first comment line): $title\n";
+my @commitfiles = map { unless (m/\s/) { '\''.$_.'\''; } else { $_; }; } (@files);
+my $cmd = join(' ', @cvs)." commit -F .msg @commitfiles";
if ($dirtypatch) {
print "NOTE: One or more hunks failed to apply cleanly.\n";
- print "Resolve the conflicts and then commit using:\n";
- print "\n $cmd\n\n";
+ print "You'll need to apply the patch in .cvsexportcommit.diff manually\n";
+ print "using a patch program. After applying the patch and resolving the\n";
+ print "problems you may commit using:";
+ print "\n cd \"$opt_w\"" if $opt_w;
+ print "\n $cmd\n";
+ print "\n git checkout $go_back_to\n" if $go_back_to;
+ print "\n";
exit(1);
}
-
if ($opt_c) {
print "Autocommit\n $cmd\n";
- print safe_pipe_capture('cvs', 'commit', '-F', '.msg', @afiles, @mfiles, @dfiles);
+ print xargs_safe_pipe_capture([@cvs, 'commit', '-F', '.msg'], @files);
if ($?) {
- cleanupcvs(@files);
die "Exiting: The commit did not succeed";
}
print "Committed successfully to CVS\n";
+ # clean up
+ unlink(".msg");
} else {
print "Ready for you to commit, just run:\n\n $cmd\n";
}
+
+# clean up
+unlink(".cvsexportcommit.diff");
+
+if ($opt_W) {
+ system("git checkout $go_back_to") && die "cannot move back to $go_back_to";
+ if (!($go_back_to =~ /^[0-9a-fA-F]{40}$/)) {
+ system("git symbolic-ref HEAD $go_back_to") &&
+ die "cannot move back to $go_back_to";
+ }
+}
+
+# CVS version 1.11.x and 1.12.x sleeps the wrong way to ensure the timestamp
+# used by CVS and the one set by subsequence file modifications are different.
+# If they are not different CVS will not detect changes.
+sleep(1);
+
sub usage {
print STDERR <<END;
-Usage: GIT_DIR=/path/to/.git ${\basename $0} [-h] [-p] [-v] [-c] [-f] [-m msgprefix] [ parent ] commit
+Usage: GIT_DIR=/path/to/.git git cvsexportcommit [-h] [-p] [-v] [-c] [-f] [-u] [-k] [-w cvsworkdir] [-m msgprefix] [ parent ] commit
END
exit(1);
}
-# ensure cvs is clean before we die
-sub cleanupcvs {
- my @files = @_;
- foreach my $f (@files) {
- system('cvs', '-q', 'update', '-C', $f);
- if ($?) {
- warn "Warning! Failed to cleanup state of $f\n";
- }
- }
-}
-
# An alternative to `command` that allows input to be passed as an array
# to work around shell problems with weird characters in arguments
# if the exec returns non-zero we die
return wantarray ? @output : join('',@output);
}
-# For any file we want to add to cvs, we must first set its permissions
-# properly, *before* the "cvs add ..." command. Otherwise, it is impossible
-# to change the permission of the file in the CVS repository using only cvs
-# commands. This should be fixed in cvs-1.12.14.
-sub set_new_file_permissions {
- my ($file, $perm) = @_;
- chmod oct($perm), $file
- or die "failed to set permissions of \"$file\": $!\n";
+sub xargs_safe_pipe_capture {
+ my $MAX_ARG_LENGTH = 65536;
+ my $cmd = shift;
+ my @output;
+ my $output;
+ while(@_) {
+ my @args;
+ my $length = 0;
+ while(@_ && $length < $MAX_ARG_LENGTH) {
+ push @args, shift;
+ $length += length($args[$#args]);
+ }
+ if (wantarray) {
+ push @output, safe_pipe_capture(@$cmd, @args);
+ }
+ else {
+ $output .= safe_pipe_capture(@$cmd, @args);
+ }
+ }
+ return wantarray ? @output : $output;
}