Rework cvsexportcommit to handle binary files for all cases.

Also adds test cases for adding removing and deleting
binary and text files plus two tests for the checks on
binary files.

Signed-off-by: Robin Rosenberg <robin.rosenberg@dewire.com>
Signed-off-by: Junio C Hamano <junkio@cox.net>

4 files changed, 195 insertions, 20 deletions

diff --git a/git-cvsexportcommit.perl b/git-cvsexportcommit.perl
index 5e23851f8c..7bac16e946 100755
--- a/git-cvsexportcommit.perl
+++ b/git-cvsexportcommit.perl
@@ -1,10 +1,10 @@
 #!/usr/bin/perl -w
 
 # Known limitations:
-# - cannot add or remove binary files
 # - does not propagate permissions
 # - tells "ready for commit" even when things could not be completed
-#   (eg addition of a binary file)
+#   (not sure this is true anymore, more testing is needed)
+# - does not handle whitespace in pathnames at all.
 
 use strict;
 use Getopt::Std;
@@ -68,9 +68,9 @@ foreach my $line (@commit) {
     if ($stage eq 'headers') {
 	if ($line =~ m/^parent (\w{40})$/) { # found a parent
 	    push @parents, $1;
-	} elsif ($line =~ m/^author (.+) \d+ \+\d+$/) {
+	} elsif ($line =~ m/^author (.+) \d+ [-+]\d+$/) {
 	    $author = $1;
-	} elsif ($line =~ m/^committer (.+) \d+ \+\d+$/) {
+	} elsif ($line =~ m/^committer (.+) \d+ [-+]\d+$/) {
 	    $committer = $1;
 	}
     } else {
@@ -139,6 +139,17 @@ foreach my $f (@files) {
 	push @dfiles, $fields[5];
     }
 }
+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
@@ -153,6 +164,10 @@ foreach my $d (@dirs) {
 }
 foreach my $f (@afiles) {
     # This should return only one value
+    if ($f =~ m,(.*)/[^/]*$,) {
+	my $p = $1;
+	next if (grep { $_ eq $p } @dirs);
+    }
     my @status = grep(m/^File/,  safe_pipe_capture('cvs', '-q', 'status' ,$f));
     if (@status > 1) { warn 'Strange! cvs status returned more than one line?'};
     if (-d dirname $f and $status[0] !~ m/Status: Unknown$/
@@ -162,6 +177,7 @@ foreach my $f (@afiles) {
 	warn "Status was: $status[0]\n";
     }
 }
+
 foreach my $f (@mfiles, @dfiles) {
     # TODO:we need to handle removed in cvs
     my @status = grep(m/^File/,  safe_pipe_capture('cvs', '-q', 'status' ,$f));
@@ -200,24 +216,31 @@ foreach my $d (@dirs) {
 
 print "'Patching' binary files\n";
 
-my @bfiles = grep(m/^Binary/, safe_pipe_capture('git-diff-tree', '-p', $parent, $commit));
-@bfiles = map { chomp } @bfiles;
 foreach my $f (@bfiles) {
     # check that the file in cvs matches the "old" file
     # extract the file to $tmpdir and compare with cmp
-    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";
-	$dirty = 1;
-	next;
+    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`;
     }
-
-    # replace with the new file
-     `git-cat-file blob $blob > $f`;
 
     # TODO: something smart with file modes
 
@@ -231,7 +254,10 @@ if ($dirty) {
 my $fuzz = $opt_p ? 0 : 2;
 
 print "Patching non-binary files\n";
-print `(git-diff-tree -p $parent -p $commit | patch -p1 -F $fuzz ) 2>&1`;
+
+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) {
@@ -242,7 +268,11 @@ if (($? >> 8) == 2) {
 }
 
 foreach my $f (@afiles) {
-    system('cvs', 'add', $f);
+    if (grep { $_ eq $f } @bfiles) {
+      system('cvs', 'add','-kb',$f);
+    } else {
+      system('cvs', 'add', $f);
+    }
     if ($?) {
 	$dirty = 1;
 	warn "Failed to cvs add $f -- you may need to do it manually";
diff --git a/t/t9200-git-cvsexportcommit.sh b/t/t9200-git-cvsexportcommit.sh
new file mode 100755
index 0000000000..6e566d4409
--- /dev/null
+++ b/t/t9200-git-cvsexportcommit.sh
@@ -0,0 +1,145 @@
+#!/bin/bash
+#
+# Copyright (c) Robin Rosenberg
+#
+test_description='CVS export comit. '
+
+. ./test-lib.sh
+
+cvs >/dev/null 2>&1
+if test $? -ne 1
+then
+    test_expect_success 'skipping git-cvsexportcommit tests, cvs not found' :
+    test_done
+    exit
+fi
+
+export CVSROOT=$(pwd)/cvsroot
+export CVSWORK=$(pwd)/cvswork
+rm -rf "$CVSROOT" "$CVSWORK"
+mkdir "$CVSROOT" &&
+cvs init &&
+cvs -Q co -d "$CVSWORK" . &&
+export GIT_DIR=$(pwd)/.git &&
+echo >empty &&
+git add empty &&
+git commit -a -m "Initial" 2>/dev/null ||
+exit 1
+
+test_expect_success \
+    'New file' \
+    'mkdir A B C D E F &&
+     echo hello1 >A/newfile1.txt &&
+     echo hello2 >B/newfile2.txt &&
+     cp ../test9200a.png C/newfile3.png &&
+     cp ../test9200a.png D/newfile4.png &&
+     git add A/newfile1.txt &&
+     git add B/newfile2.txt &&
+     git add C/newfile3.png &&
+     git add D/newfile4.png &&
+     git commit -a -m "Test: New file" &&
+     id=$(git rev-list --max-count=1 HEAD) &&
+     (cd "$CVSWORK" &&
+     git cvsexportcommit -c $id &&
+     test "$(echo $(sort A/CVS/Entries|cut -d/ -f2,3,5))" = "newfile1.txt/1.1/" &&
+     test "$(echo $(sort B/CVS/Entries|cut -d/ -f2,3,5))" = "newfile2.txt/1.1/" &&
+     test "$(echo $(sort C/CVS/Entries|cut -d/ -f2,3,5))" = "newfile3.png/1.1/-kb" &&
+     test "$(echo $(sort D/CVS/Entries|cut -d/ -f2,3,5))" = "newfile4.png/1.1/-kb" &&
+     diff A/newfile1.txt ../A/newfile1.txt &&
+     diff B/newfile2.txt ../B/newfile2.txt &&
+     diff C/newfile3.png ../C/newfile3.png &&
+     diff D/newfile4.png ../D/newfile4.png
+     )'
+
+test_expect_success \
+    'Remove two files, add two and update two' \
+    'echo Hello1 >>A/newfile1.txt &&
+     rm -f B/newfile2.txt &&
+     rm -f C/newfile3.png &&
+     echo Hello5  >E/newfile5.txt &&
+     cp ../test9200b.png D/newfile4.png &&
+     cp ../test9200a.png F/newfile6.png &&
+     git add E/newfile5.txt &&
+     git add F/newfile6.png &&
+     git commit -a -m "Test: Remove, add and update" &&
+     id=$(git rev-list --max-count=1 HEAD) &&
+     (cd "$CVSWORK" &&
+     git cvsexportcommit -c $id &&
+     test "$(echo $(sort A/CVS/Entries|cut -d/ -f2,3,5))" = "newfile1.txt/1.2/" &&
+     test "$(echo $(sort B/CVS/Entries|cut -d/ -f2,3,5))" = "" &&
+     test "$(echo $(sort C/CVS/Entries|cut -d/ -f2,3,5))" = "" &&
+     test "$(echo $(sort D/CVS/Entries|cut -d/ -f2,3,5))" = "newfile4.png/1.2/-kb" &&
+     test "$(echo $(sort E/CVS/Entries|cut -d/ -f2,3,5))" = "newfile5.txt/1.1/" &&
+     test "$(echo $(sort F/CVS/Entries|cut -d/ -f2,3,5))" = "newfile6.png/1.1/-kb" &&
+     diff A/newfile1.txt ../A/newfile1.txt &&
+     diff D/newfile4.png ../D/newfile4.png &&
+     diff E/newfile5.txt ../E/newfile5.txt &&
+     diff F/newfile6.png ../F/newfile6.png
+     )'
+
+# Should fail (but only on the git-cvsexportcommit stage)
+test_expect_success \
+    'Fail to change binary more than one generation old' \
+    'cat F/newfile6.png >>D/newfile4.png &&
+     git commit -a -m "generatiion 1" &&
+     cat F/newfile6.png >>D/newfile4.png &&
+     git commit -a -m "generation 2" &&
+     id=$(git rev-list --max-count=1 HEAD) &&
+     (cd "$CVSWORK" &&
+     ! git cvsexportcommit -c $id
+     )'
+
+# Should fail, but only on the git-cvsexportcommit stage
+test_expect_success \
+    'Fail to remove binary file more than one generation old' \
+    'git reset --hard HEAD^ &&
+     cat F/newfile6.png >>D/newfile4.png &&
+     git commit -a -m "generation 2 (again)" &&
+     rm -f D/newfile4.png &&
+     git commit -a -m "generation 3" &&
+     id=$(git rev-list --max-count=1 HEAD) &&
+     (cd "$CVSWORK" &&
+     ! git cvsexportcommit -c $id
+     )'
+
+# We reuse the state from two tests back here
+
+# This test is here because a patch for only binary files will
+# fail with gnu patch, so cvsexportcommit must handle that.
+test_expect_success \
+    'Remove only binary files' \
+    'git reset --hard HEAD^^^ &&
+     rm -f D/newfile4.png &&
+     git commit -a -m "test: remove only a binary file" &&
+     id=$(git rev-list --max-count=1 HEAD) &&
+     (cd "$CVSWORK" &&
+     git cvsexportcommit -c $id &&
+     test "$(echo $(sort A/CVS/Entries|cut -d/ -f2,3,5))" = "newfile1.txt/1.2/" &&
+     test "$(echo $(sort B/CVS/Entries|cut -d/ -f2,3,5))" = "" &&
+     test "$(echo $(sort C/CVS/Entries|cut -d/ -f2,3,5))" = "" &&
+     test "$(echo $(sort D/CVS/Entries|cut -d/ -f2,3,5))" = "" &&
+     test "$(echo $(sort E/CVS/Entries|cut -d/ -f2,3,5))" = "newfile5.txt/1.1/" &&
+     test "$(echo $(sort F/CVS/Entries|cut -d/ -f2,3,5))" = "newfile6.png/1.1/-kb" &&
+     diff A/newfile1.txt ../A/newfile1.txt &&
+     diff E/newfile5.txt ../E/newfile5.txt &&
+     diff F/newfile6.png ../F/newfile6.png
+     )'
+
+test_expect_success \
+    'Remove only a text file' \
+    'rm -f A/newfile1.txt &&
+     git commit -a -m "test: remove only a binary file" &&
+     id=$(git rev-list --max-count=1 HEAD) &&
+     (cd "$CVSWORK" &&
+     git cvsexportcommit -c $id &&
+     test "$(echo $(sort A/CVS/Entries|cut -d/ -f2,3,5))" = "" &&
+     test "$(echo $(sort B/CVS/Entries|cut -d/ -f2,3,5))" = "" &&
+     test "$(echo $(sort C/CVS/Entries|cut -d/ -f2,3,5))" = "" &&
+     test "$(echo $(sort D/CVS/Entries|cut -d/ -f2,3,5))" = "" &&
+     test "$(echo $(sort E/CVS/Entries|cut -d/ -f2,3,5))" = "newfile5.txt/1.1/" &&
+     test "$(echo $(sort F/CVS/Entries|cut -d/ -f2,3,5))" = "newfile6.png/1.1/-kb" &&
+     diff E/newfile5.txt ../E/newfile5.txt &&
+     diff F/newfile6.png ../F/newfile6.png
+     )'
+
+test_done
diff --git a/t/test9200a.png b/t/test9200a.png
new file mode 100644
index 0000000000..7b181d15ce
--- /dev/null
+++ b/t/test9200a.png
diff --git a/t/test9200b.png b/t/test9200b.png
new file mode 100644
index 0000000000..ac22ccbd3e
--- /dev/null
+++ b/t/test9200b.png