added back massTagger feature and changed stats to now also includes …

…percentage of known morphemes weighted by frequency (field level)

anki/plugins/morphman3/morph/config.py

@@ -81,7 +81,7 @@
     'JtMW':         { 'enabled':True, 'set due based on mmi': False, 'ignore maturity': True },
     'JSPfEC':       { 'enabled':True, 'set due based on mmi': False },
     'Tae Kim Cloze':{ 'enabled':True, 'set due based on mmi': False },
-    'Yotsubato':    { 'enabled':True, 'set due based on mmi': False },
+    'Yotsubato':    { 'enabled':True, 'set due based on mmi': True },
     'Rikaisama':    { 'enabled':True, 'set due based on mmi': False },
     #'Kore': { 'enabled':True, 'set due based on mmi': False, 'morph_fields':[u'SentenceExpression'] },
     'Kore':         { 'enabled':True, 'set due based on mmi': False },
@@ -92,4 +92,7 @@
     'Sentences':            { 'new card merged fill':True },
     'Sentences::subs2srs':  { 'new card merged fill':True },
     'Sentences::vn2srs':    { 'new card merged fill':True },
+    'ExtraVocab':           { 'new card merged fill':True },
+    'ExtraVocab::_Yotsubato':   { 'new card merged fill':True },
+    'ExtraVocab::_Kore':        { 'new card merged fill':True },
 }

anki/plugins/morphman3/morph/massTagger.py

@@ -1,30 +1,29 @@
 #-*- coding: utf-8 -*-
-from morphemes import getMorphemes, ms2str, MorphDb
+from morphemes import getMorphemes, MorphDb
 from util import addBrowserSelectionCmd, cfg, cfg1, infoMsg, QInputDialog, QFileDialog, QLineEdit
 import util
 
-def pre( b ):
+def pre( b ): # :: Browser -> State
     tags, ok = QInputDialog.getText( b, 'Enter tags', 'Tags', QLineEdit.Normal, 'hasMorph' )
     if not ok or not tags: return
     path = QFileDialog.getOpenFileName( caption='Open db', directory=util.dbsPath )
     if not path: return
     db = MorphDb( path )
     return { 'b':b, 'db':db, 'tags':unicode(tags) }
 
-def per( st, n ):
-    n.delTag( st['tags'] )
-
-    if n['k+N'] == '1': # FIXME this special but commonly wanted logic must be a cfg option
-        ms = getMorphemes( n['focusMorph'], None, cfg1('morph_blacklist') )
-        for m in ms:
+def per( st, n ): # :: State -> Note -> State
+    #n.delTag( st['tags'] ) # clear tags if they already exist?
+
+    for field in cfg( n.mid, None, 'morph_fields' ):
+        for m in getMorphemes( n[ field ], None, cfg1('morph_blacklist') ):
             if m in st['db'].db:
                 n.addTag( st['tags'] )
                 break
-
     n.flush()
     return st
 
-def post( st ):
+def post( st ): # :: State -> State
+    infoMsg( 'Tagged all notes containing morphemes in that db' )
     return st
 
 addBrowserSelectionCmd( 'Mass Tagger', pre, per, post, tooltip='Tag all cards that contain morphemes from db', shortcut=None )

anki/plugins/morphman3/morph/stats.py

@@ -34,20 +34,25 @@ def updateStats( knownDb=None ):
 
     d['totalKnown'] = len( knownDb.db )
 
-    # Load Goal.*.db dbs, get total morphemes required, and compare vs known.db
+    # Load Goal.*.db dbs, get morphemes required, and compare vs known.db
     d['goals'] = {}
     goalDbPaths = glob.glob( os.path.join( cfg1('path_dbs'), 'Goal.*.db' ) )
 
     for path in goalDbPaths:
         name = os.path.basename( path )[5:][:-3]
         gdb = MorphDb( path )
 
-        required = set( gdb.db.keys() )
-        allKnown = set( knownDb.db.keys() )
-
-        numReq = len( required )
-        numKnown = len( required.intersection( allKnown ) )
-        d['goals'][ name ] = { 'total': numReq, 'known': numKnown }
+        # track total unique morphemes + when weighted by frequency
+        # NOTE: a morpheme may occur multiple times within the same sentence, but this frequency is wrt note fields
+        numUniqueReq, numUniqueKnown, numFreqReq, numFreqKnown = 0, 0, 0, 0
+        for m,locs in gdb.db.iteritems():
+            numUniqueReq += 1
+            numFreqReq   += len( locs )
+            if m in knownDb.db:
+                numUniqueKnown += 1
+                numFreqKnown   += len( locs )
+
+        d['goals'][ name ] = { 'total':numUniqueReq, 'known':numUniqueKnown, 'freqTotal':numFreqReq, 'freqKnown':numFreqKnown }
 
     saveStats( d )
     mw.progress.finish()
@@ -61,7 +66,8 @@ def getStatsLink():
     lines = []
     for goalName, g in sorted( d['goals'].items() ):
         #lines.append( '%s %d/%d %d%%' % ( goalName, g['known'], g['total'], 100.*g['known']/g['total'] ) )
-        lines.append( '%s %d%%' % ( goalName, 100.*g['known']/g['total'] ) )
+        #lines.append( '%s %d%%' % ( goalName, 100.*g['known']/g['total'] ) )
+        lines.append( '%s %d%% %d%%' % ( goalName, 100.*g['known']/g['total'], 100.*g['freqKnown']/g['freqTotal'] ) )
     details = '\n'.join( lines )
     return ( name, details )
 

anki/plugins/morphman3/morphman.py

@@ -31,5 +31,6 @@ def main():
     import morph.batchPlay
     import morph.newMorphHelper
     import morph.stats
+    import morph.massTagger
 
 main()