new project: datastore analysis scripts

4 files changed, 849 insertions, 0 deletions

diff --git a/dsparse.py b/dsparse.py
new file mode 100755
index 0000000..6ed5f57
--- /dev/null
+++ b/dsparse.py
@@ -0,0 +1,214 @@
+#!/usr/bin/env python
+#Copyright (c) 2012, Walter Bender
+
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# You should have received a copy of the GNU General Public License
+# along with this library; if not, write to the Free Software
+# Foundation, 51 Franklin Street, Suite 500 Boston, MA 02110-1335 USA
+
+# Simple parser of datastore backups
+
+import os
+import glob
+import time
+
+
+DIROFINTEREST = 'datastore-current'
+
+
+class ParseMain():
+
+    def __init__(self):
+        self._dsdict = {}
+
+        abspath = os.path.abspath('.')
+        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
+                        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
+
+        for k, v in self._dsdict.iteritems():
+            for i in v:
+                line = '%s, ' % (k)
+                if 'activity' in i:
+                    line += '%s, ' % (i['activity'])
+                else:
+                    line += ', '
+                if 'mime_type' in i:
+                    line += '%s, ' % (i['mime_type'])
+                else:
+                    line += ', '
+                if 'activity count' in i:
+                    line += '%s, ' % (i['activity count'])
+                else:
+                    line += ', '
+                if 'creation_time' in i:
+                    line += '%s, ' % (i['creation_time'])
+                else:
+                    line += ', '
+                if 'mtime' in i:
+                    line += '%s, ' % (i['mtime'])
+                else:
+                    line += ', '
+                if 'score' in i:
+                    line += '%s, ' % (i['score'])
+                else:
+                    line += ', '
+                print line
+
+
+def hascomponent(path, component):
+    ''' Return metadata attribute, if any '''
+    if not os.path.exists(os.path.join(path, 'metadata')):
+        return False
+    if not os.path.exists(os.path.join(path, 'metadata', component)):
+        return False
+    fd = open(os.path.join(path, 'metadata', component))
+    data = fd.readline()
+    fd.close()
+    if len(data) == 0:
+        return False
+    return data
+
+
+
+TACAT = {'clean':'forward', 'forward':'forward', 'back':'forward',
+         'left':'forward', 'right':'forward', 'arc': 'arc',
+         'xcor': 'coord', 'ycor': 'coord', 'heading': 'coord', 
+         'setxy': 'setxy', 'seth': 'setxy', 'penup': 'pen', 'pendown': 'pen',
+         'setpensize': 'pen', 'setcolor': 'pen', 'pensize': 'pen',
+         'color': 'pen', 'setshade': 'pen', 'setgray': 'pen', 'shade': 'pen',
+         'gray': 'pen', 'fillscreen': 'pen', 'startfill': 'fill',
+         'stopfill': 'fill', 'plus2': 'number', 'minus2': 'number',
+         'product2': 'number', 'division2': 'number', 'remainder2': 'number',
+         'sqrt': 'number', 'identity2': 'number', 'and2': 'boolean',
+         'or2': 'boolean', 'not': 'boolean', 'greater2': 'boolean',
+         'less2': 'boolean', 'equal2': 'boolean', 'random': 'random',
+         'repeat': 'repeat', 'forever': 'repeat', 'if': 'ifthen',
+         'ifelse': 'ifthen', 'while': 'ifthen', 'until': 'ifthen',
+         'hat': 'action', 'stack': 'action', 'storein': 'box', 'box': 'box',
+         'luminance': 'sensor', 'mousex': 'sensor', 'mousey': 'sensor',
+         'mousebutton2': 'sensor', 'keyboard': 'sensor', 'kbinput': 'sensor',
+         'readpixel': 'sensor', 'see': 'sensor', 'time': 'sensor',
+         'sound': 'sensor', 'volume': 'sensor', 'pitch': 'sensor',
+         'resistance': 'sensor', 'voltage': 'sensor', 'video': 'media',
+         'wait': 'media', 'camera': 'media', 'journal': 'media',
+         'audio': 'media', 'show': 'media', 'setscale': 'media',
+         'savepix': 'media', 'savesvg': 'media', 'mediawait': 'media',
+         'mediapause': 'media', 'mediastop': 'media', 'mediaplay': 'media',
+         'speak': 'media', 'sinewave': 'media', 'description': 'media',
+         'push':'extras', 'pop':'extras', 'printheap':'extras',
+         'clearheap':'extras', 'isheapempty2':'extras', 'chr':'extras',
+         'int':'extras', 'myfunction': 'python', 'userdefined': 'python',
+         'loadblock': 'python', 'loadpalette': 'python'}
+TAPAL = {'forward': 'turtlep', 'arc': 'turtlep', 'coord': 'turtlep',
+         'setxy': 'turtlep', 'pen': 'penp', 'fill': 'penp', 'number': 'numberp',
+         'random': 'numberp', 'boolean': 'numberp', 'repeat': 'flowp',
+         'ifthen': 'flowp', 'action': 'boxp', 'box': 'boxp',
+         'sensor': 'sensorp', 'media': 'mediap', 'extras': 'extrasp',
+         'python': 'extrasp'}
+TASCORE = {'forward': 3, 'arc': 3, 'setxy': 2.5, 'coord': 4, 'turtlep': 5,
+           'pen': 2.5, 'fill': 2.5, 'penp': 5,
+           'number': 2.5, 'boolean': 2.5, 'random': 2.5, 'numberp': 0,
+           'repeat': 2.5, 'ifthen': 7.5, 'flowp': 10,
+           'box': 7.5, 'action': 7.5, 'boxp': 0,
+           'media': 5, 'mediap': 0,
+           'python': 5, 'extras': 5, 'extrasp': 0,
+           'sensor': 5, 'sensorp': 0}
+           
+
+def hasturtleblocks(path):
+    ''' Parse turtle block data and generate score based on rubric '''
+
+    if not os.path.exists(os.path.join(path, 'data')):
+        return None
+    fd = open(os.path.join(path, 'data'))
+    blocks = []
+    # block name is second token in each line
+    for line in fd:
+        tokens = line.split(',')
+        if len(tokens) > 1:
+            token = tokens[1].strip('" [')
+            blocks.append(token)
+
+    score = 0
+    cats = []
+    pals = []
+
+    for b in blocks:
+        if b in TACAT:
+            if not TACAT[b] in cats:
+                cats.append(TACAT[b])
+    for c in cats:
+        if c in TAPAL:
+            if not TAPAL[c] in pals:
+                pals.append(TAPAL[c])
+    for c in cats:
+        if c in TASCORE:
+            score += TASCORE[c]
+    for p in pals:
+        if p in TASCORE:
+            score += TASCORE[p]
+
+    return str(score)
+
+
+def isactivity(path):
+    ''' Return activity name '''
+    activity = hascomponent(path, 'activity')
+    if not activity:
+        return False
+    else:
+        return activity.split('.')[-1]
+
+
+def isdsdir(path):
+    ''' Only interested if it is a datastore directory '''
+    if not os.path.isdir(path):
+        return False
+    if not os.path.exists(os.path.join(path, DIROFINTEREST)):
+        return False
+    return True
+
+
+if __name__ == '__main__':
+    ParseMain()
diff --git a/olpcdsparse.py b/olpcdsparse.py
new file mode 100755
index 0000000..244c7cb
--- /dev/null
+++ b/olpcdsparse.py
@@ -0,0 +1,213 @@
+#!/usr/bin/env python
+#Copyright (c) 2012, Walter Bender
+
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# You should have received a copy of the GNU General Public License
+# along with this library; if not, write to the Free Software
+# Foundation, 51 Franklin Street, Suite 500 Boston, MA 02110-1335 USA
+
+# Simple parser of datastore backups
+
+import os
+import glob
+import time
+
+
+DIROFINTEREST = 'datastore'
+
+
+class ParseMain():
+
+    def __init__(self):
+        self._dsdict = {}
+
+        homepath = os.environ['HOME']
+        for path in glob.glob(os.path.join(homepath, '.sugar', '*')):
+            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
+                        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
+
+        for k, v in self._dsdict.iteritems():
+            for i in v:
+                line = '%s, ' % (k)
+                if 'activity' in i:
+                    line += '%s, ' % (i['activity'])
+                else:
+                    line += ', '
+                if 'mime_type' in i:
+                    line += '%s, ' % (i['mime_type'])
+                else:
+                    line += ', '
+                if 'activity count' in i:
+                    line += '%s, ' % (i['activity count'])
+                else:
+                    line += ', '
+                if 'creation_time' in i:
+                    line += '%s, ' % (i['creation_time'])
+                else:
+                    line += ', '
+                if 'mtime' in i:
+                    line += '%s, ' % (i['mtime'])
+                else:
+                    line += ', '
+                if 'score' in i:
+                    line += '%s, ' % (i['score'])
+                else:
+                    line += ', '
+                print line
+
+
+def hascomponent(path, component):
+    ''' Return metadata attribute, if any '''
+    if not os.path.exists(os.path.join(path, 'metadata')):
+        return False
+    if not os.path.exists(os.path.join(path, 'metadata', component)):
+        return False
+    fd = open(os.path.join(path, 'metadata', component))
+    data = fd.readline()
+    fd.close()
+    if len(data) == 0:
+        return False
+    return data
+
+
+TACAT = {'clean':'forward', 'forward':'forward', 'back':'forward',
+         'left':'forward', 'right':'forward', 'arc': 'arc',
+         'xcor': 'coord', 'ycor': 'coord', 'heading': 'coord', 
+         'setxy': 'setxy', 'seth': 'setxy', 'penup': 'pen', 'pendown': 'pen',
+         'setpensize': 'pen', 'setcolor': 'pen', 'pensize': 'pen',
+         'color': 'pen', 'setshade': 'pen', 'setgray': 'pen', 'shade': 'pen',
+         'gray': 'pen', 'fillscreen': 'pen', 'startfill': 'fill',
+         'stopfill': 'fill', 'plus2': 'number', 'minus2': 'number',
+         'product2': 'number', 'division2': 'number', 'remainder2': 'number',
+         'sqrt': 'number', 'identity2': 'number', 'and2': 'boolean',
+         'or2': 'boolean', 'not': 'boolean', 'greater2': 'boolean',
+         'less2': 'boolean', 'equal2': 'boolean', 'random': 'random',
+         'repeat': 'repeat', 'forever': 'repeat', 'if': 'ifthen',
+         'ifelse': 'ifthen', 'while': 'ifthen', 'until': 'ifthen',
+         'hat': 'action', 'stack': 'action', 'storein': 'box', 'box': 'box',
+         'luminance': 'sensor', 'mousex': 'sensor', 'mousey': 'sensor',
+         'mousebutton2': 'sensor', 'keyboard': 'sensor', 'kbinput': 'sensor',
+         'readpixel': 'sensor', 'see': 'sensor', 'time': 'sensor',
+         'sound': 'sensor', 'volume': 'sensor', 'pitch': 'sensor',
+         'resistance': 'sensor', 'voltage': 'sensor', 'video': 'media',
+         'wait': 'media', 'camera': 'media', 'journal': 'media',
+         'audio': 'media', 'show': 'media', 'setscale': 'media',
+         'savepix': 'media', 'savesvg': 'media', 'mediawait': 'media',
+         'mediapause': 'media', 'mediastop': 'media', 'mediaplay': 'media',
+         'speak': 'media', 'sinewave': 'media', 'description': 'media',
+         'push':'extras', 'pop':'extras', 'printheap':'extras',
+         'clearheap':'extras', 'isheapempty2':'extras', 'chr':'extras',
+         'int':'extras', 'myfunction': 'python', 'userdefined': 'python',
+         'loadblock': 'python', 'loadpalette': 'python'}
+TAPAL = {'forward': 'turtlep', 'arc': 'turtlep', 'coord': 'turtlep',
+         'setxy': 'turtlep', 'pen': 'penp', 'fill': 'penp', 'number': 'numberp',
+         'random': 'numberp', 'boolean': 'numberp', 'repeat': 'flowp',
+         'ifthen': 'flowp', 'action': 'boxp', 'box': 'boxp',
+         'sensor': 'sensorp', 'media': 'mediap', 'extras': 'extrasp',
+         'python': 'extrasp'}
+TASCORE = {'forward': 3, 'arc': 3, 'setxy': 2.5, 'coord': 4, 'turtlep': 5,
+           'pen': 2.5, 'fill': 2.5, 'penp': 5,
+           'number': 2.5, 'boolean': 2.5, 'random': 2.5, 'numberp': 0,
+           'repeat': 2.5, 'ifthen': 7.5, 'flowp': 10,
+           'box': 7.5, 'action': 7.5, 'boxp': 0,
+           'media': 5, 'mediap': 0,
+           'python': 5, 'extras': 5, 'extrasp': 0,
+           'sensor': 5, 'sensorp': 0}
+           
+
+def hasturtleblocks(path):
+    ''' Parse turtle block data and generate score based on rubric '''
+
+    if not os.path.exists(os.path.join(path, 'data')):
+        return None
+    fd = open(os.path.join(path, 'data'))
+    blocks = []
+    # block name is second token in each line
+    for line in fd:
+        tokens = line.split(',')
+        if len(tokens) > 1:
+            token = tokens[1].strip('" [')
+            blocks.append(token)
+
+    score = 0
+    cats = []
+    pals = []
+
+    for b in blocks:
+        if b in TACAT:
+            if not TACAT[b] in cats:
+                cats.append(TACAT[b])
+    for c in cats:
+        if c in TAPAL:
+            if not TAPAL[c] in pals:
+                pals.append(TAPAL[c])
+    for c in cats:
+        if c in TASCORE:
+            score += TASCORE[c]
+    for p in pals:
+        if p in TASCORE:
+            score += TASCORE[p]
+
+    return str(score)
+
+
+def isactivity(path):
+    ''' Return activity name '''
+    activity = hascomponent(path, 'activity')
+    if not activity:
+        return False
+    else:
+        return activity.split('.')[-1]
+
+
+def isdsdir(path):
+    ''' Only interested if it is a datastore directory '''
+    if not os.path.isdir(path):
+        return False
+    if not os.path.exists(os.path.join(path, DIROFINTEREST)):
+        return False
+    return True
+
+
+if __name__ == '__main__':
+    ParseMain()
diff --git a/olpctaparse.py b/olpctaparse.py
new file mode 100755
index 0000000..421cf96
--- /dev/null
+++ b/olpctaparse.py
@@ -0,0 +1,202 @@
+#!/usr/bin/env python
+#Copyright (c) 2012, Walter Bender
+
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# You should have received a copy of the GNU General Public License
+# along with this library; if not, write to the Free Software
+# Foundation, 51 Franklin Street, Suite 500 Boston, MA 02110-1335 USA
+
+# Simple parser of datastore backups
+
+import os
+import glob
+import time
+
+DIROFINTEREST = 'datastore'
+
+
+class ParseMain():
+
+    def __init__(self):
+        self._dsdict = {}
+
+        homepath = os.environ['HOME']
+        for path in glob.glob(os.path.join(homepath, '.sugar', '*')):
+            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:
+                        if not isactivity(dsobj) == 'TurtleArtActivity':
+                            continue
+                        mime_type = hascomponent(dsobj, 'mime_type')
+                        if mime_type != 'application/x-turtle-art':
+                            continue
+                        self._dsdict[os.path.basename(path)].append({})
+                        activity = isactivity(dsobj)
+                        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
+                        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
+
+        for k, v in self._dsdict.iteritems():
+            for i in v:
+                line = '%s, ' % (k)
+                if 'activity' in i:
+                    line += '%s, ' % (i['activity'])
+                else:
+                    line += ', '
+                if 'activity count' in i:
+                    line += '%s, ' % (i['activity count'])
+                else:
+                    line += ', '
+                if 'creation_time' in i:
+                    line += '%s, ' % (i['creation_time'])
+                else:
+                    line += ', '
+                if 'score' in i:
+                    for j in i['score']:
+                        line += '%s, ' % (str(j))
+                else:
+                    line += ', '
+                print line
+
+
+def hascomponent(path, component):
+    ''' Return metadata attribute, if any '''
+    if not os.path.exists(os.path.join(path, 'metadata')):
+        return False
+    if not os.path.exists(os.path.join(path, 'metadata', component)):
+        return False
+    fd = open(os.path.join(path, 'metadata', component))
+    data = fd.readline()
+    fd.close()
+    if len(data) == 0:
+        return False
+    return data
+
+
+TACAT = {'clean':'forward', 'forward':'forward', 'back':'forward',
+         'left':'forward', 'right':'forward', 'arc': 'arc',
+         'xcor': 'coord', 'ycor': 'coord', 'heading': 'coord', 
+         'setxy': 'setxy', 'seth': 'setxy', 'penup': 'pen', 'pendown': 'pen',
+         'setpensize': 'pen', 'setcolor': 'pen', 'pensize': 'pen',
+         'color': 'pen', 'setshade': 'pen', 'setgray': 'pen', 'shade': 'pen',
+         'gray': 'pen', 'fillscreen': 'pen', 'startfill': 'fill',
+         'stopfill': 'fill', 'plus2': 'number', 'minus2': 'number',
+         'product2': 'number', 'division2': 'number', 'remainder2': 'number',
+         'sqrt': 'number', 'identity2': 'number', 'and2': 'boolean',
+         'or2': 'boolean', 'not': 'boolean', 'greater2': 'boolean',
+         'less2': 'boolean', 'equal2': 'boolean', 'random': 'random',
+         'repeat': 'repeat', 'forever': 'repeat', 'if': 'ifthen',
+         'ifelse': 'ifthen', 'while': 'ifthen', 'until': 'ifthen',
+         'hat': 'action', 'stack': 'action', 'storein': 'box', 'box': 'box',
+         'luminance': 'sensor', 'mousex': 'sensor', 'mousey': 'sensor',
+         'mousebutton2': 'sensor', 'keyboard': 'sensor', 'kbinput': 'sensor',
+         'readpixel': 'sensor', 'see': 'sensor', 'time': 'sensor',
+         'sound': 'sensor', 'volume': 'sensor', 'pitch': 'sensor',
+         'resistance': 'sensor', 'voltage': 'sensor', 'video': 'media',
+         'wait': 'media', 'camera': 'media', 'journal': 'media',
+         'audio': 'media', 'show': 'media', 'setscale': 'media',
+         'savepix': 'media', 'savesvg': 'media', 'mediawait': 'media',
+         'mediapause': 'media', 'mediastop': 'media', 'mediaplay': 'media',
+         'speak': 'media', 'sinewave': 'media', 'description': 'media',
+         'push':'extras', 'pop':'extras', 'printheap':'extras',
+         'clearheap':'extras', 'isheapempty2':'extras', 'chr':'extras',
+         'int':'extras', 'myfunction': 'python', 'userdefined': 'python',
+         'loadblock': 'python', 'loadpalette': 'python'}
+TAPAL = {'forward': 'turtlep', 'arc': 'turtlep', 'coord': 'turtlep',
+         'setxy': 'turtlep', 'pen': 'penp', 'fill': 'penp', 'number': 'numberp',
+         'random': 'numberp', 'boolean': 'numberp', 'repeat': 'flowp',
+         'ifthen': 'flowp', 'action': 'boxp', 'box': 'boxp',
+         'sensor': 'sensorp', 'media': 'mediap', 'extras': 'extrasp',
+         'python': 'extrasp'}
+TASCORE = {'forward': 3, 'arc': 3, 'setxy': 2.5, 'coord': 4, 'turtlep': 5,
+           'pen': 2.5, 'fill': 2.5, 'penp': 5,
+           'number': 2.5, 'boolean': 2.5, 'random': 2.5, 'numberp': 0,
+           'repeat': 2.5, 'ifthen': 7.5, 'flowp': 10,
+           'box': 7.5, 'action': 7.5, 'boxp': 0,
+           'media': 5, 'mediap': 0,
+           'python': 5, 'extras': 5, 'extrasp': 0,
+           'sensor': 5, 'sensorp': 0}
+PALS = ['turtlep', 'penp', 'numberp', 'flowp', 'boxp', 'sensorp', 'mediap',
+        'extrasp']
+
+
+def hasturtleblocks(path):
+    ''' Parse turtle block data and generate score based on rubric '''
+
+    if not os.path.exists(os.path.join(path, 'data')):
+        return None
+    fd = open(os.path.join(path, 'data'))
+    blocks = []
+    # block name is second token in each line
+    for line in fd:
+        tokens = line.split(',')
+        if len(tokens) > 1:
+            token = tokens[1].strip('" [')
+            blocks.append(token)
+
+    score = []
+    for i in range(len(PALS)):
+        score.append(0)
+    cats = []
+    pals = []
+
+    for b in blocks:
+        if b in TACAT:
+            if not TACAT[b] in cats:
+                cats.append(TACAT[b])
+    for c in cats:
+        if c in TAPAL:
+            if not TAPAL[c] in pals:
+                pals.append(TAPAL[c])
+    for c in cats:
+        if c in TASCORE:
+            score[PALS.index(TAPAL[c])] += TASCORE[c]
+    for p in pals:
+        if p in TASCORE:
+            score[PALS.index(p)] += TASCORE[p]
+
+    return score
+
+
+def isactivity(path):
+    ''' Return activity name '''
+    activity = hascomponent(path, 'activity')
+    if not activity:
+        return False
+    else:
+        return activity.split('.')[-1]
+
+
+def isdsdir(path):
+    ''' Only interested if it is a datastore directory '''
+    if not os.path.isdir(path):
+        return False
+    if not os.path.exists(os.path.join(path, DIROFINTEREST)):
+        return False
+    return True
+
+
+if __name__ == '__main__':
+    ParseMain()
diff --git a/taparse.py b/taparse.py
new file mode 100755
index 0000000..f89cf3d
--- /dev/null
+++ b/taparse.py
@@ -0,0 +1,220 @@
+#!/usr/bin/env python
+#Copyright (c) 2012, Walter Bender
+
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# You should have received a copy of the GNU General Public License
+# along with this library; if not, write to the Free Software
+# Foundation, 51 Franklin Street, Suite 500 Boston, MA 02110-1335 USA
+
+# Simple parser of turtleart backups
+
+import os
+import glob
+import time
+
+
+DIROFINTEREST = 'datastore-current'
+
+
+class ParseMain():
+
+    def __init__(self):
+        self._dsdict = {}
+
+        abspath = os.path.abspath('.')
+        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:
+                        if not isactivity(dsobj) == 'TurtleArtActivity':
+                            continue
+                        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
+                        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
+
+        for k, v in self._dsdict.iteritems():
+            for i in v:
+                line = '%s, ' % (k)
+                if 'activity' in i:
+                    line += '%s, ' % (i['activity'])
+                else:
+                    line += ', '
+                if 'mime_type' in i:
+                    line += '%s, ' % (i['mime_type'])
+                else:
+                    line += ', '
+                if 'activity count' in i:
+                    line += '%s, ' % (i['activity count'])
+                else:
+                    line += ', '
+                if 'creation_time' in i:
+                    line += '%s, ' % (i['creation_time'])
+                else:
+                    line += ', '
+                if 'mtime' in i:
+                    line += '%s, ' % (i['mtime'])
+                else:
+                    line += ', '
+                if 'score' in i:
+                    for j in i['score']:
+                        line += '%s, ' % (str(j))
+                else:
+                    line += ', '
+                print line
+
+
+def hascomponent(path, component):
+    ''' Return metadata attribute, if any '''
+    if not os.path.exists(os.path.join(path, 'metadata')):
+        return False
+    if not os.path.exists(os.path.join(path, 'metadata', component)):
+        return False
+    fd = open(os.path.join(path, 'metadata', component))
+    data = fd.readline()
+    fd.close()
+    if len(data) == 0:
+        return False
+    return data
+
+
+TACAT = {'clean':'forward', 'forward':'forward', 'back':'forward',
+         'left':'forward', 'right':'forward', 'arc': 'arc',
+         'xcor': 'coord', 'ycor': 'coord', 'heading': 'coord', 
+         'setxy': 'setxy', 'seth': 'setxy', 'penup': 'pen', 'pendown': 'pen',
+         'setpensize': 'pen', 'setcolor': 'pen', 'pensize': 'pen',
+         'color': 'pen', 'setshade': 'pen', 'setgray': 'pen', 'shade': 'pen',
+         'gray': 'pen', 'fillscreen': 'pen', 'startfill': 'fill',
+         'stopfill': 'fill', 'plus2': 'number', 'minus2': 'number',
+         'product2': 'number', 'division2': 'number', 'remainder2': 'number',
+         'sqrt': 'number', 'identity2': 'number', 'and2': 'boolean',
+         'or2': 'boolean', 'not': 'boolean', 'greater2': 'boolean',
+         'less2': 'boolean', 'equal2': 'boolean', 'random': 'random',
+         'repeat': 'repeat', 'forever': 'repeat', 'if': 'ifthen',
+         'ifelse': 'ifthen', 'while': 'ifthen', 'until': 'ifthen',
+         'hat': 'action', 'stack': 'action', 'storein': 'box', 'box': 'box',
+         'luminance': 'sensor', 'mousex': 'sensor', 'mousey': 'sensor',
+         'mousebutton2': 'sensor', 'keyboard': 'sensor', 'kbinput': 'sensor',
+         'readpixel': 'sensor', 'see': 'sensor', 'time': 'sensor',
+         'sound': 'sensor', 'volume': 'sensor', 'pitch': 'sensor',
+         'resistance': 'sensor', 'voltage': 'sensor', 'video': 'media',
+         'wait': 'media', 'camera': 'media', 'journal': 'media',
+         'audio': 'media', 'show': 'media', 'setscale': 'media',
+         'savepix': 'media', 'savesvg': 'media', 'mediawait': 'media',
+         'mediapause': 'media', 'mediastop': 'media', 'mediaplay': 'media',
+         'speak': 'media', 'sinewave': 'media', 'description': 'media',
+         'push':'extras', 'pop':'extras', 'printheap':'extras',
+         'clearheap':'extras', 'isheapempty2':'extras', 'chr':'extras',
+         'int':'extras', 'myfunction': 'python', 'userdefined': 'python',
+         'loadblock': 'python', 'loadpalette': 'python'}
+TAPAL = {'forward': 'turtlep', 'arc': 'turtlep', 'coord': 'turtlep',
+         'setxy': 'turtlep', 'pen': 'penp', 'fill': 'penp', 'number': 'numberp',
+         'random': 'numberp', 'boolean': 'numberp', 'repeat': 'flowp',
+         'ifthen': 'flowp', 'action': 'boxp', 'box': 'boxp',
+         'sensor': 'sensorp', 'media': 'mediap', 'extras': 'extrasp',
+         'python': 'extrasp'}
+TASCORE = {'forward': 3, 'arc': 3, 'setxy': 2.5, 'coord': 4, 'turtlep': 5,
+           'pen': 2.5, 'fill': 2.5, 'penp': 5,
+           'number': 2.5, 'boolean': 2.5, 'random': 2.5, 'numberp': 0,
+           'repeat': 2.5, 'ifthen': 7.5, 'flowp': 10,
+           'box': 7.5, 'action': 7.5, 'boxp': 0,
+           'media': 5, 'mediap': 0,
+           'python': 5, 'extras': 5, 'extrasp': 0,
+           'sensor': 5, 'sensorp': 0}
+PALS = ['turtlep', 'penp', 'numberp', 'flowp', 'boxp', 'sensorp', 'mediap',
+        'extrasp']
+
+
+def hasturtleblocks(path):
+    ''' Parse turtle block data and generate score based on rubric '''
+
+    if not os.path.exists(os.path.join(path, 'data')):
+        return None
+    fd = open(os.path.join(path, 'data'))
+    blocks = []
+    # block name is second token in each line
+    for line in fd:
+        tokens = line.split(',')
+        if len(tokens) > 1:
+            token = tokens[1].strip('" [')
+            blocks.append(token)
+
+    score = []
+    for i in range(len(PALS)):
+        score.append(0)
+    cats = []
+    pals = []
+
+    for b in blocks:
+        if b in TACAT:
+            if not TACAT[b] in cats:
+                cats.append(TACAT[b])
+    for c in cats:
+        if c in TAPAL:
+            if not TAPAL[c] in pals:
+                pals.append(TAPAL[c])
+    for c in cats:
+        if c in TASCORE:
+            score[PALS.index(TAPAL[c])] += TASCORE[c]
+    for p in pals:
+        if p in TASCORE:
+            score[PALS.index(p)] += TASCORE[p]
+
+    return score
+
+
+def isactivity(path):
+    ''' Return activity name '''
+    activity = hascomponent(path, 'activity')
+    if not activity:
+        return False
+    else:
+        return activity.split('.')[-1]
+
+
+def isdsdir(path):
+    ''' Only interested if it is a datastore directory '''
+    if not os.path.isdir(path):
+        return False
+    if not os.path.exists(os.path.join(path, DIROFINTEREST)):
+        return False
+    return True
+
+
+if __name__ == '__main__':
+    ParseMain()