combo-layer: partial import for '--history init'

The new "since_revision" property can be used to cut off the imported
history at some point. This is useful to keep the resulting repository
smaller while still preserving enough history that "git annotate"
reports the right author and commit for most lines.

The initial, squashed import commit shows up with "unknown" as author
in the "git annotate" output. It has the repository name as prefix
in the subject line; importing that commit works best with a
layer hook which does not add the repository name again when
it is already present. Adding it here is useful for hooks
which do not extend the subject line.

Signed-off-by: Patrick Ohly <patrick.ohly@intel.com>
Signed-off-by: Ross Burton <ross.burton@intel.com>

1 files changed, 40 insertions, 0 deletions

diff --git a/scripts/combo-layer b/scripts/combo-layer
index 6d24ce3ee15..cbff61803b0 100755
--- a/scripts/combo-layer
+++ b/scripts/combo-layer
@@ -284,6 +284,46 @@ def action_init(conf, args):
                 runcmd("git branch -D %s" % refname, ldir)
                 # Make that the head revision.
                 runcmd("git checkout -b %s %s" % (name, initialrev))
+                # Optional: cut the history by replacing the given
+                # start point(s) with commits providing the same
+                # content (aka tree), but with commit information that
+                # makes it clear that this is an artifically created
+                # commit and nothing the original authors had anything
+                # to do with.
+                since_rev = repo.get('since_revision', '')
+                if since_rev:
+                    committer = runcmd('git var GIT_AUTHOR_IDENT').strip()
+                    # Same time stamp, no name.
+                    author = re.sub('.* (\d+ [+-]\d+)', r'unknown <unknown> \1', committer)
+                    logger.info('author %s' % author)
+                    for rev in since_rev.split():
+                        # Resolve in component repo...
+                        rev = runcmd('git log --oneline --no-abbrev-commit -n1 %s' % rev, ldir).split()[0]
+                        # ... and then get the tree in current
+                        # one. The commit should be in both repos with
+                        # the same tree, but better check here.
+                        tree = runcmd('git show -s --pretty=format:%%T %s' % rev).strip()
+                        with tempfile.NamedTemporaryFile() as editor:
+                            editor.write('''cat >$1 <<EOF
+tree %s
+author %s
+committer %s
+
+%s: squashed import of component
+
+This commit copies the entire set of files as found in
+%s %s
+
+For more information about previous commits, see the
+upstream repository.
+
+Commit created by combo-layer.
+EOF
+''' % (tree, author, committer, name, name, since_rev))
+                            editor.flush()
+                            os.environ['GIT_EDITOR'] = 'sh %s' % editor.name
+                            runcmd('git replace --edit %s' % rev)
+
                 # Optional: rewrite history to change commit messages or to move files.
                 if 'hook' in repo or dest_dir and dest_dir != ".":
                     filter_branch = ['git', 'filter-branch', '--force']