gitsm.py: Rework the shallow fetcher and test case

A custom shallow submodule is no longer necessary, as the regular git
fetcher is used and shallow handling works with the same code.

The only general difference between the regular change is simply declaring a
clone as shallow, when appropriate.

This also removes a potential race condition in copying repositories
vs cloning them.

The gitsm shallow fetcher test was revised to verify that the submodule
is shallow cloned along with the primary repository.

The first step of this change was to be sure to clean the gitsubmodule download
directory, as was previously done with the may gitsource directory.

Additional test components were added to verify commit counts, and an
obsolete (and likely incorrect) test for the .git/modules directory to be
empty was also removed.

Signed-off-by: Mark Hatle <mark.hatle@windriver.com>
Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>
(cherry picked from commit f9cc4684dcf4281acc557cda8cb35602354ac3d6)
Signed-off-by: Scott Murray <scott.murray@konsulko.com>
Signed-off-by: Armin Kuster <akuster@mvista.com>

2 files changed, 13 insertions, 63 deletions

diff --git a/lib/bb/fetch2/gitsm.py b/lib/bb/fetch2/gitsm.py
index c172ab166..83571f834 100644
--- a/lib/bb/fetch2/gitsm.py
+++ b/lib/bb/fetch2/gitsm.py
@@ -150,68 +150,7 @@ class GitSM(Git):
 
     def download(self, ud, d):
         Git.download(self, ud, d)
-
-        if not ud.shallow or ud.localpath != ud.fullshallow:
-            self.update_submodules(ud, d)
-
-    def copy_submodules(self, submodules, ud, name, destdir, d):
-        if ud.bareclone:
-            repo_conf = destdir
-        else:
-            repo_conf = os.path.join(destdir, '.git')
-
-        if submodules and not os.path.exists(os.path.join(repo_conf, 'modules')):
-            os.mkdir(os.path.join(repo_conf, 'modules'))
-
-        for module, md in submodules.items():
-            srcpath = os.path.join(ud.clonedir, 'modules', md['path'])
-            modpath = os.path.join(repo_conf, 'modules', md['path'])
-
-            # Check if the module is initialized
-            try:
-                module_hash = runfetchcmd("%s ls-tree -z -d %s %s" % (ud.basecmd, ud.revisions[name], md['path']), d, quiet=True, workdir=ud.clonedir)
-            except:
-                # If the command fails, we don't have a valid file to check.  If it doesn't
-                # fail -- it still might be a failure, see next check...
-                module_hash = ""
-
-            if not module_hash:
-                logger.debug(1, "submodule %s is defined, but is not initialized in the repository. Skipping", module)
-                continue
-
-            if os.path.exists(srcpath):
-                if os.path.exists(os.path.join(srcpath, '.git')):
-                    srcpath = os.path.join(srcpath, '.git')
-
-                target = modpath
-                if os.path.exists(modpath):
-                    target = os.path.dirname(modpath)
-
-                os.makedirs(os.path.dirname(target), exist_ok=True)
-                runfetchcmd("cp -fpLR %s %s" % (srcpath, target), d)
-            elif os.path.exists(modpath):
-                # Module already exists, likely unpacked from a shallow mirror clone
-                pass
-            else:
-                # This is fatal, as we do NOT want git-submodule to hit the network
-                raise bb.fetch2.FetchError('Submodule %s does not exist in %s or %s.' % (module, srcpath, modpath))
-
-    def clone_shallow_local(self, ud, dest, d):
-        super(GitSM, self).clone_shallow_local(ud, dest, d)
-
-        # Copy over the submodules' fetched histories too.
-        repo_conf = os.path.join(dest, '.git')
-
-        submodules = []
-        for name in ud.names:
-            try:
-                gitmodules = runfetchcmd("%s show %s:.gitmodules" % (ud.basecmd, ud.revision), d, quiet=True, workdir=dest)
-            except:
-                # No submodules to update
-                continue
-
-            submodules = self.parse_gitmodules(gitmodules)
-            self.copy_submodules(submodules, ud, name, dest, d)
+        self.update_submodules(ud, d)
 
     def unpack_submodules(self, repo_conf, ud, d):
         submodules = []
@@ -294,6 +233,9 @@ class GitSM(Git):
             # Correct the submodule references to the local download version...
             runfetchcmd("%(basecmd)s config submodule.%(module)s.url %(url)s" % {'basecmd': ud.basecmd, 'module': module, 'url' : local_paths[module]}, d, workdir=ud.destdir)
 
+            if ud.shallow:
+                runfetchcmd("%(basecmd)s config submodule.%(module)s.shallow true" % {'basecmd': ud.basecmd, 'module': module}, d, workdir=ud.destdir)
+
             # Ensure the submodule repository is NOT set to bare, since we're checking it out...
             runfetchcmd("%s config core.bare false" % (ud.basecmd), d, quiet=True, workdir=os.path.join(repo_conf, 'modules', paths[module]))
 
diff --git a/lib/bb/tests/fetch.py b/lib/bb/tests/fetch.py
index 311c70137..5fb5d04cb 100644
--- a/lib/bb/tests/fetch.py
+++ b/lib/bb/tests/fetch.py
@@ -1316,6 +1316,7 @@ class GitShallowTest(FetcherTest):
         # fetch and unpack, from the shallow tarball
         bb.utils.remove(self.gitdir, recurse=True)
         bb.utils.remove(ud.clonedir, recurse=True)
+        bb.utils.remove(ud.clonedir.replace('gitsource', 'gitsubmodule'), recurse=True)
 
         # confirm that the unpacked repo is used when no git clone or git
         # mirror tarball is available
@@ -1470,6 +1471,7 @@ class GitShallowTest(FetcherTest):
         self.git('config --add remote.origin.url "%s"' % smdir, cwd=smdir)
         self.git('config --add remote.origin.fetch "+refs/heads/*:refs/remotes/origin/*"', cwd=smdir)
         self.add_empty_file('asub', cwd=smdir)
+        self.add_empty_file('bsub', cwd=smdir)
 
         self.git('submodule init', cwd=self.srcdir)
         self.git('submodule add file://%s' % smdir, cwd=self.srcdir)
@@ -1479,10 +1481,16 @@ class GitShallowTest(FetcherTest):
         uri = 'gitsm://%s;protocol=file;subdir=${S}' % self.srcdir
         fetcher, ud = self.fetch_shallow(uri)
 
+        # Verify the main repository is shallow
         self.assertRevCount(1)
-        assert './.git/modules/' in bb.process.run('tar -tzf %s' % os.path.join(self.dldir, ud.mirrortarballs[0]))[0]
+
+        # Verify the gitsubmodule directory is present
         assert os.listdir(os.path.join(self.gitdir, 'gitsubmodule'))
 
+        # Verify the submodule is also shallow
+        self.assertRevCount(1, cwd=os.path.join(self.gitdir, 'gitsubmodule'))
+
+
     if any(os.path.exists(os.path.join(p, 'git-annex')) for p in os.environ.get('PATH').split(':')):
         def test_shallow_annex(self):
             self.add_empty_file('a')