parse backup datastores

1 files changed, 58 insertions, 42 deletions

diff --git a/dsparse.py b/dsparse.py
index 9b8671a..0ee919f 100755
--- a/dsparse.py
+++ b/dsparse.py
@@ -29,48 +29,64 @@ class ParseMain():
         for path in glob.glob(os.path.join(abspath, '*')):
             if isdsdir(path):
                 self._dsdict[os.path.basename(path)] = []
-                dsobjdirs = glob.glob(
-                    os.path.join(path, DIROFINTEREST, '??'))
-                for dsobjdir in dsobjdirs:
-                    dsobjs = glob.glob(os.path.join(dsobjdir, '*'))
-                    for dsobj in dsobjs:
-                        self._dsdict[os.path.basename(path)].append({})
-                        activity = isactivity(dsobj)
-                        if not activity:
-                            self._dsdict[os.path.basename(path)][-1][
-                                'activity'] = 'media object'
-                        else:
-                            self._dsdict[os.path.basename(path)][-1][
-                                'activity'] = activity
-                        if activity == 'TurtleArtActivity':
-                            score = hasturtleblocks(dsobj)
-                            if score:
-                                self._dsdict[os.path.basename(path)][-1][
-                                    'score'] = score
-                        if activity == 'AbiWordActivity':
-                            score = hasmenuitems(dsobj)
-                            if score:
-                                self._dsdict[os.path.basename(path)][-1][
-                                    'score'] = score
-                        mime_type = hascomponent(dsobj, 'mime_type')
-                        if mime_type:
-                            self._dsdict[os.path.basename(path)][-1][
-                                'mime_type'] = mime_type
-                        mtime = hascomponent(dsobj, 'mtime')
-                        if mtime:
-                            self._dsdict[os.path.basename(path)][-1][
-                                'mtime'] = mtime
-                        creation_time = hascomponent(dsobj, 'creation_time')
-                        if creation_time:
-                            self._dsdict[os.path.basename(path)][-1][
-                                'creation_time'] = \
-                                time.strftime('%Y-%m-%dT%H:%M:%S',
-                                              time.gmtime(float(creation_time)))
-                        activity_count = hascomponent(dsobj, 'activity count')
-                        if activity_count:
-                            self._dsdict[os.path.basename(path)][-1][
-                                'activity count'] = activity_count
-
+                self.dsobj_list = []
+                # First, parse datastore-current; then look for
+                # additional objects in the backup dirs
+                # FIXME: go from most recent to least recent
+                alldirs = glob.glob(os.path.join(path, '*'))
+                self._parse_dir(path, DIROFINTEREST)
+                for directory in alldirs:
+                    if directory !=  DIROFINTEREST:
+                        self._parse_dir(path, directory)
+        self._output()
+
+    def _parse_dir(self, path, directory):
+        dsobjdirs = glob.glob(
+            os.path.join(path, directory, '??'))
+        for dsobjdir in dsobjdirs:
+            dsobjs = glob.glob(os.path.join(dsobjdir, '*'))
+            for dsobj in dsobjs:
+                basename = os.path.basename(dsobj)
+                if not basename in self.dsobj_list:
+                    self.dsobj_list.append(basename)
+                else:
+                    continue  # don't overwrite current object
+                self._dsdict[os.path.basename(path)].append({})
+                activity = isactivity(dsobj)
+                if not activity:
+                    self._dsdict[os.path.basename(path)][-1]['activity'] = \
+                        'media object'
+                else:
+                    self._dsdict[os.path.basename(path)][-1]['activity'] = \
+                        activity
+                if activity == 'TurtleArtActivity':
+                    score = hasturtleblocks(dsobj)
+                    if score:
+                        self._dsdict[os.path.basename(path)][-1]['score'] = \
+                            score
+                if activity == 'AbiWordActivity':
+                    score = hasmenuitems(dsobj)
+                    if score:
+                        self._dsdict[os.path.basename(path)][-1]['score'] = \
+                            score
+                mime_type = hascomponent(dsobj, 'mime_type')
+                if mime_type:
+                    self._dsdict[os.path.basename(path)][-1]['mime_type'] = \
+                        mime_type
+                mtime = hascomponent(dsobj, 'mtime')
+                if mtime:
+                    self._dsdict[os.path.basename(path)][-1]['mtime'] = mtime
+                creation_time = hascomponent(dsobj, 'creation_time')
+                if creation_time:
+                    self._dsdict[os.path.basename(path)][-1]['creation_time'] \
+                        = time.strftime('%Y-%m-%dT%H:%M:%S',
+                                        time.gmtime(float(creation_time)))
+                activity_count = hascomponent(dsobj, 'activity count')
+                if activity_count:
+                    self._dsdict[os.path.basename(path)][-1]['activity count'] \
+                        = activity_count
+
+    def _output(self):
         for k, v in self._dsdict.iteritems():
             for i in v:
                 line = '%s, ' % (k)