Still more tweaking of git_changelog.

1. Don't assume there's only one candidate match; check them all and use the
one with the closest timestamp.  Avoids funny output when someone makes
several successive commits with the same log message, as certain people
have been known to do.

2. When the same commit (with the same SHA1) is reachable from multiple
branch tips, don't report it for all the branches; instead report it only
for the first such branch.  Given our development practices, this case
arises only for commits that occurred before a given branch split off from
master.  The original coding blamed old commits on *all* the branches,
which isn't terribly useful; the new coding blames such a commit only on
master.

diff --git a/src/tools/git_changelog b/src/tools/git_changelog
index 766f66a4da79cc9ecdffc46c2c3f3d56bfc88130..a52b4a534c44d389f86e267485f853286ca4b3df 100755 (executable)
--- a/src/tools/git_changelog
+++ b/src/tools/git_changelog
@@ -47,7 +47,6 @@ for my $branch (@BRANCHES) {
    my $pid =
      IPC::Open2::open2(my $git_out, my $git_in, @git, "origin/$branch")
          || die "can't run @git origin/$branch: $!";
-   my $commitnum = 0;
    my %commit;
    while (my $line = <$git_out>) {
        if ($line =~ /^commit\s+(.*)/) {
@@ -56,7 +55,6 @@ for my $branch (@BRANCHES) {
                'branch' => $branch,
                'commit' => $1,
                'message' => '',
-               'commitnum' => $commitnum++,
            );
        }
        elsif ($line =~ /^Author:\s+(.*)/) {
@@ -127,21 +125,37 @@ sub push_commit {
    my $ht = hash_commit($c);
    my $ts = parse_datetime($c->{'date'});
    my $cc;
+   # Note that this code will never merge two commits on the same branch,
+   # even if they have the same hash (author/message) and nearby
+   # timestamps.  This means that there could be multiple potential
+   # matches when we come to add a commit from another branch.  Prefer
+   # the closest-in-time one.
    for my $candidate (@{$all_commits{$ht}}) {
-       if (abs($ts - $candidate->{'timestamp'}) < $timestamp_slop
-           && !exists $candidate->{'branch_position'}{$c->{'branch'}})
+       my $diff = abs($ts - $candidate->{'timestamp'});
+       if ($diff < $timestamp_slop &&
+           !exists $candidate->{'branch_position'}{$c->{'branch'}})
        {
+           if (!defined $cc ||
+           $diff < abs($ts - $cc->{'timestamp'})) {
            $cc = $candidate;
-           last;
+           }
        }
    }
    if (!defined $cc) {
        $cc = {
            'header' => sprintf("Author: %s\n", $c->{'author'}),
            'message' => $c->{'message'},
+           'commit' => $c->{'commit'},
            'timestamp' => $ts
        };
        push @{$all_commits{$ht}}, $cc;
+   } elsif ($cc->{'commit'} eq $c->{'commit'}) {
+       # If this is exactly the same commit we saw before on another
+       # branch, ignore it.  Hence, a commit that's reachable from more
+       # than one branch head will be reported only for the first
+       # head it's reachable from.  This will give the desired results
+       # so long as @BRANCHES is ordered with master first.
+       return;
    }
    $cc->{'header'} .= sprintf "Branch: %s [%s] %s\n",
        $c->{'branch'}, substr($c->{'commit'}, 0, 9), $c->{'date'};